my current collection of papers on Twitter and tweets, including 253 papers.

twitter_lib.bib

%% This BibTeX bibliography file in UTF-8 format was created using Papers.
%% http://mekentosj.com/papers/

@article{turner_praise_2012,
author = {Julia Turner}, 
journal = {The New York Times},
title = {In Praise of the Hashtag},
chapter = {Magazine},
year = {2012},
keywords = {Twitter}, 
date-added = {2013-04-13 21:02:21 +0100},
date-modified = {2013-04-13 21:02:22 +0100},
URL = {http://www.nytimes.com/2012/11/04/magazine/in-praise-of-the-hashtag.html},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p30617},
rating = {0}
}

@article{Huberman:2008p1602,
author = {B Huberman and DM Romero and F Wu}, 
journal = {First Monday},
title = {Social networks that matter: Twitter under the microscope},
abstract = {Scholars, advertisers and political activists see massive online so- cial networks as a representation of social interactions that can be used to study the propagation of ideas, social bond dynamics and viral mar- keting, among others. But the linked structures of social networks do not reveal actual interactions among people. Scarcity of attention and the daily rythms of life and work makes people default to interacting with those few that matter and that reciprocate their attention. A study of social interactions within Twitter reveals that the driver of usage is a sparse and hidden network of connections underlying the ``declared'' set of friends and followers.},
year = {2008},
month = {Jan},
date-added = {2010-11-03 11:45:29 +0000},
date-modified = {2012-04-18 14:09:51 +0100},
pmid = {10935152536708189294related:bgw0k0t3wZcJ},
URL = {http://arxiv.org/pdf/0812.1045},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2008/Huberman/Social%20networks%20that%20matter%20Twitter%20under%20the%20microscope.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p1602},
read = {Yes},
rating = {0}
}

@article{Zhang:2009p3423,
author = {Y Zhang}, 
journal = {American Journal of Economics and Business {\ldots}},
title = {Determinants of Poster Reputation on Internet Stock Message Boards},
abstract = {I investigate the determinants of poster reputation in a user-rewarding reputation system on Thelion!WallStreetPit stock message board. My empirical analyses deal with two hypotheses: First, is a poster's reputation affected by his/her characteristics at the time the message was posted? Second, is reputation also associated with the characteristics of the stock to which the message refers? Approach: To answer these two questions, I tested two sets of explanatory variables in relation to poster reputation in two fixed-effects panel regressions. Results: First, the poster's popularity in the community, the poster's sentiment, information quality not quantity and one day follow-up opinion on the stock all have positive impacts on the poster's reputation; Second, recommending stocks with high price to earnings ratio and high institutional investors holding percentage reduce the chance of receiving reputation credits while promoting high liquidity stocks did the opposite. Conclusion: This study discarded light on the future construction of a credit-weighted sentiment index should the researchers consider weighing each poster's sentiment based on its reputation. This study also helped us to build a more effective and better functional reputation system in the future. Finally, findings in this study allowed us to better examine the relationship between sentiment and stock returns in future studies.},
year = {2009},
month = {Jan},
date-added = {2010-11-20 23:00:13 +0000},
date-modified = {2012-04-18 14:09:19 +0100},
pmid = {related:LV3GjzLCaOYJ},
URL = {http://scipub.org/fulltext/ajeba/ajeba12114-121.pdf},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2009/Zhang/Determinants%20of%20Poster%20Reputation%20on.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p3423},
read = {Yes},
rating = {0}
}

@article{Osborne:2012p29842,
author = {M Osborne and S Petrovic and R McCreadie and C Macdonald and I Ounis}, 
title = {Bieber no more: First Story Detection using Twitter and Wikipedia},
abstract = {Twitter is a well known source of information regarding breaking news stories. This aspect of Twitter makes it ideal for identifying events as they happen. However, a key prob- lem with Twitter-driven event detection approaches is that they produce many spurious events, i.e., events that are wrongly detected or simply are of no interest to anyone. In this paper, we examine whether Wikipedia (when viewed as a stream of page views) can be used to improve the qual- ity of discovered events in Twitter. Our results suggest that Wikipedia is a powerful filtering mechanism, allowing for easy blocking of large numbers of spurious events. Our re- sults also indicate that events within Wikipedia tend to lag behind Twitter.},
year = {2012},
date-added = {2012-10-26 12:49:47 +0100},
date-modified = {2012-11-03 14:43:27 +0000},
pmid = {related:wiH6R5qzjO0J},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2012/Osborne/Bieber%20no%20more%20First%20Story%20Detection%20using%20Twitter%20and%20Wikipedia.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p29842},
rating = {0}
}

@article{Roberts:2012p29833,
author = {K Roberts and M.A Roach and J Johnson and J Guthrie and S.M Harabagiu}, 
title = {EmpaTweet: Annotating and Detecting Emotions on Twitter},
abstract = {The rise of micro-blogging in recent years has resulted in significant access to emotion-laden text. Unlike emotion expressed in other textual sources (e.g., blogs, quotes in newswire, email, product reviews, or even clinical text), micro-blogs differ by (1) placing a strict limit on length, resulting radically in new forms of emotional expression, and (2) encouraging users to express their daily thoughts in real-time, often resulting in far more emotion statements than might normally occur. In this paper, we introduce a corpus collected from Twitter with annotated micro-blog posts (or ``tweets'') annotated at the tweet-level with seven emotions: ANGER, DISGUST, FEAR, JOY, LOVE, SADNESS, and SURPRISE. We analyze how emotions are distributed in the data we annotated and compare it to the distributions in other emotion-annotated corpora. We also used the annotated corpus to train a classifier that automatically discovers the emotions in tweets. In addition, we present an analysis of the linguistic style used for expressing emotions our corpus. We hope that these observations will lead to the design of novel emotion detection techniques that account for linguistic style and psycholinguistic theories.},
year = {2012},
date-added = {2012-10-26 12:49:46 +0100},
date-modified = {2012-11-03 14:46:52 +0000},
pmid = {related:edB5jSq3_f4J},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2012/Roberts/EmpaTweet%20Annotating%20and%20Detecting%20Emotions%20on%20Twitter.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p29833},
rating = {0}
}

@article{Sakaki:2010p3637,
author = {T Sakaki and M Okazaki and Y Matsuo}, 
journal = {Proceedings of the 19th international conference on World wide web},
title = {Earthquake shakes Twitter users: real-time event detection by social sensors},
abstract = {Twitter, a popular microblogging service, has received much attention recently. An important characteristic of Twitter is its real-time nature. For example, when an earthquake occurs, people make many Twitter posts (tweets) related to the earthquake, which enables detection of earthquake occurrence promptly, simply by observing the tweets. As described in this paper, we investigate the real-time interaction of events such as earthquakes in Twitter and propose an algorithm to monitor tweets and to detect a target event. To detect a target event, we devise a classifier of tweets based on features such as the keywords in a tweet, the number of words, and their context. Subsequently, we produce a probabilistic spatiotemporal model for the target event that can find the center and the trajectory of the event location. We consider each Twitter user as a sensor and apply Kalman filtering and particle filtering, which are widely used for location estimation in ubiquitous/pervasive computing. The particle filter works better than other comparable methods for estimating the centers of earthquakes and the trajectories of typhoons. As an application, we con- struct an earthquake reporting system in Japan. Because of the numerous earthquakes and the large number of Twitter users throughout the country, we can detect an earthquake with high probability (96% of earthquakes of Japan Meteorological Agency (JMA) seismic intensity scale 3 or more are detected) merely by monitoring tweets. Our system detects earthquakes promptly and sends e-mails to registered users. Notification is delivered much faster than the announcements that are broadcast by the JMA.},
pages = {851--860},
year = {2010},
keywords = {algorithm, sa, earthquake}, 
date-added = {2010-11-26 16:47:05 +0000},
date-modified = {2012-04-18 14:10:39 +0100},
pmid = {2874786646722566359related:11jvUjlL5ScJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2010/Sakaki/Earthquake%20shakes%20Twitter%20users%20real-time%20event%20detection%20by%20social%20sensors.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p3637},
read = {Yes},
rating = {4}
}

@article{Lampos:2010p4793,
author = {V Lampos and N Cristianini}, 
journal = {IAPR Cognitive Information Processing},
title = {Tracking the flu pandemic by monitoring the Social Web},
abstract = {Tracking the spread of an epidemic disease like seasonal or pandemic influenza is an important task that can reduce its impact and help authorities plan their response. In particular, early detection and geolocation of an outbreak are important aspects of this monitoring activity. Various methods are routinely employed for this monitoring, such as counting the consultation rates of general practitioners. We report on a monitoring tool to measure the prevalence of disease in a population by analysing the contents of social networking tools, such as Twitter. Our method is based on the analysis of hundreds of thousands of tweets per day, searching for symptom-related statements, and turning statistical information into a flu-score. We have tested it in the United Kingdom for 24 weeks during the H1N1 flu pandemic. We compare our flu-score with data from the Health Protection Agency, obtaining on average a statistically significant linear correlation which is greater than 95%. This method uses completely independent data to that commonly used for these purposes, and can be used at close time intervals, hence providing inexpensive and timely information about the state of an epidemic.},
year = {2010},
date-added = {2010-12-16 23:36:37 +0000},
date-modified = {2012-04-18 14:10:49 +0100},
pmid = {4775622528174229304related:OIctFWNrRkIJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2010/Lampos/Tracking%20the%20flu%20pandemic%20by.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p4793},
read = {Yes},
rating = {0}
}

@article{Ritter:2011p22699,
author = {A Ritter and S Clark and Masusam and O Etzioni}, 
journal = {cs.washington.edu},
title = {Extracting a Calendar from Twitter},
abstract = {We present a simple and scalable approach to automatically extracting calendar entries from Twitter. By extracting Named Entities and resolving temporal expressions within Twitter's noisy text, we are able to extract an approximate calendar of the most popular events occurring in the near future. We describe the challenges in adapting NLP tools to Twitter, and present an approach to measuring the associ- ation strength between an entity and a date. Precision and web recall of calendar entry extraction are evaluated, where we more than double precision over an ngram baseline.
The results of applying our approach on millions of Tweets collected in realtime can be viewed at http://statuscalendar. com. In addition our NLP tools which have been adapted
to Twitter are available at http://github.com/aritter/ twitter_nlp.},
year = {2011},
date-added = {2011-09-18 10:51:17 +0100},
date-modified = {2012-04-18 14:11:02 +0100},
URL = {http://www.cs.washington.edu/homes/aritter/calendar.pdf},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Ritter/Extracting%20a%20Calendar%20from%20Twitter.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p22699},
read = {Yes},
rating = {0}
}

@article{Yang:2010p21403,
author = {C Yang and RC Harkreader and GF Gu}, 
journal = {faculty.cs.tamu.edu},
title = {Die Free or Live Hard? Empirical Evaluation and New Design for Fighting Evolving Twitter Spammers},
abstract = {To date, as one of the most popular Online Social Networks (OSNs), Twitter is paying its dues as more and more spammers set their sights on this microblogging site. The Twitter spammers can achieve their malicious goals such as sending spam, spreading malware, hosting botnet command and control (C{\&}C) channels, and launching other underground illicit activities. Due to the significance and indispensability of detecting and suspending those spam accounts, many researchers along with the engi- neers in Twitter Corporation have devoted themselves to keeping Twitter as spam-free online communities. Most of the existing studies utilize machine learning techniques to detect Twitter spammers. ``While the priest climbs a post, the devil climbs ten''. Twitter spammers are evolving to evade existing detection features. In this paper, we first make a comprehensive and empirical analysis of the evasion tactics utilized by Twitter spammers. We further design several new detection features to detect more Twitter spammers. In addition, to deeply understand the effectiveness and difficulties of using machine learning features to detect spammers, we analzye the robustness of 24 detection features that are commonly utilized in the literature as well as our proposed ones. Through our experiments, we show that our new designed features are much more effective to be used to detect (even evasive) Twitter spammers. According to our evaluation, while keeping an even lower false positive rate, the detection rate using our new feature set significantly increases to 85%, compared with a detection rate of 51% and 73% for the worst existing detector and the best existing detector, respectively. To the best of our knowledge, this work is the first empirical study and evaluation of the effect of evasion tactics utilized by Twitter spammers and is a valuable supplement to this line of research.},
year = {2010},
date-added = {2011-07-30 21:51:00 +0100},
date-modified = {2012-04-18 14:09:29 +0100},
URL = {http://faculty.cs.tamu.edu/guofei/paper/TwitterML_TechReport_2011.pdf},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2010/Yang/Die%20Free%20or%20Live%20Hard?.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p21403},
rating = {0}
}

@article{Leetaru:2013p31943,
author = {Kalev Leetaru and Shaowen Wang and Guofeng Cao and Anand Padmanabhan and Eric Shook}, 
journal = {First Monday},
title = {Mapping the global Twitter heartbeat: The geography of Twitter},
abstract = {In just under seven years, Twitter has grown to count nearly three percent of the entire global population among its active users who have sent more than 170 billion 140--character messages. Today the service plays such a significant role in American culture that the Library of Congress has assembled a permanent archive of the site back to its first tweet, updated daily. With its open API, Twitter has become one of the most popular data sources for social research, yet the majority of the literature has focused on it as a text or network graph source, with only limited efforts to date focusing exclusively on the geography of Twitter, assessing the various sources of geographic information on the service and their accuracy. More than three percent of all tweets are found to have native location information available, while a naive geocoder based on a simple major cities gazetteer and relying on the user--provided Location and Profile fields is able to geolocate more than a third of all tweets with high accuracy when measured against the GPS--based baseline. Geographic proximity is found to play a minimal role both in who users communicate with and what they communicate about, providing evidence that social media is shifting the communicative landscape.},
number = {5},
volume = {18},
year = {2013},
date-added = {2013-07-10 10:06:38 +0100},
date-modified = {2013-07-10 10:06:57 +0100},
pmid = {7818578310765052772related:ZIO5jYwrgWwJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2013/Leetaru/Mapping%20the%20global%20Twitter%20heartbeat%20The%20geography%20of%20Twitter.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p31943},
rating = {0}
}

@article{Green:2013p31133,
author = {R Green and J Sheppard}, 
journal = {The Twenty-Sixth International FLAIRS {\ldots}},
title = {Comparing Frequency-and Style-Based Features for Twitter Author Identification},
abstract = {Author identification is a subfield of Natural Language Processing (NLP) that uses machine learning tech- niques to identify the author of a text. Most previous research focused on long texts with the assumption that a minimum text length threshold exists under which au- thor identification would no longer be effective. This pa- per examines author identification in short texts far be- low this threshold, focusing on messages retrieved from Twitter (maximum length: 140 characters) to determine the most effective feature set for author identification. Both Bag-of-Words (BOW) and Style Marker feature sets were extracted and evaluated through a series of 15 experiments involving up to 12 authors with large and small dataset sizes. Support Vector Machines (SVM) were used for all experiments. Our results achieve clas- sification accuracies approaching that of longer texts, even for small dataset sizes of 60 training instances per author. Style Marker feature sets were found to be sig- nificantly more useful than BOW feature sets as well as orders of magnitude faster, and are therefore suggested for potential applications in future research.},
year = {2013},
month = {Jan},
keywords = {General Conference Papers}, 
date-added = {2013-06-04 16:15:10 +0100},
date-modified = {2013-06-11 10:02:42 +0100},
URL = {http://www.aaai.org/ocs/index.php/FLAIRS/FLAIRS13/paper/download/5917/6043},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2013/Green/Comparing%20Frequency-and%20Style-Based%20Features%20for%20Twitter%20Author%20Identification.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p31133},
rating = {0}
}

@article{Davies:2011p24221,
author = {A Davies and Z Ghahramani}, 
journal = {Social Network Mining and Analysis},
title = {Language-independent Bayesian sentiment mining of Twitter},
abstract = {This paper outlines a new language-independent model for sentiment analysis of short, social-network statuses. We demonstrate this on data from Twitter, modelling happy vs sad sentiment, and show that in some circumstances this outperforms similar Naive Bayes models by more than 10%.
We also propose an extension to allow the modelling of differ- ent sentiment distributions in different geographic regions, while incorporating information from neighbouring regions.
We outline the considerations when creating a system analysing Twitter data and present a scalable system of data acquisi- tion and prediction that can monitor the sentiment of tweets in real time.},
year = {2011},
date-added = {2011-10-18 21:44:38 +0100},
date-modified = {2013-06-10 14:57:43 +0100},
URL = {http://www.alexdavies.net/wordpress/wp-content/uploads/2011/09/Language-Indepedent-Bayesian-Sentiment-Mining-of-Twitter.pdf},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Davies/Language-independent%20Bayesian%20sentiment%20mining%20of%20Twitter.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p24221},
rating = {0}
}

@article{Bollen:2009p812,
author = {J Bollen and A Pepe and H Mao}, 
journal = {Arxiv preprint arXiv:0911.1583},
title = {Modeling public mood and emotion: Twitter sentiment and socio-economic phenomena},
abstract = {Microblogging is a form of online communication by which users broadcast brief text updates, also known as tweets, to the public or a selected circle of contacts. A variegated mosaic of microblogging uses has emerged since the launch of Twitter in 2006: daily chatter, conversation, information sharing, and news commentary, among others. Regardless of their content and intended use, tweets often convey perti- nent information about their author's mood status. As such, tweets can be regarded as temporally-authentic microscopic instantiations of public mood state. In this article, we per- form a sentiment analysis of all public tweets broadcasted by Twitter users between August 1 and December 20, 2008. For every day in the timeline, we extract six dimensions of mood (tension, depression, anger, vigor, fatigue, confusion) using an extended version of the Profile of Mood States (POMS), a well-established psychometric instrument. We compare our results to fluctuations recorded by stock market and crude oil price indices and major events in media and popular cul- ture, such as the U.S. Presidential Election of November 4, 2008 and Thanksgiving Day. We find that events in the social, political, cultural and economic sphere do have a significant, immediate and highly specific effect on the various dimensions of public mood. We speculate that large scale analyses of mood can provide a solid platform to model collective emotive trends in terms of their predictive value with regards to existing social as well as economic indicators.},
year = {2009},
month = {Jan},
date-added = {2010-10-30 18:28:27 +0100},
date-modified = {2013-07-17 14:16:15 +0100},
pmid = {10120069473201398336related:QKJxRJG1cYwJ},
URL = {http://arxiv.org/pdf/0911.1583},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2009/Bollen/Modeling%20public%20mood%20and%20emotion%20Twitter%20sentiment%20and%20socio-economic%20phenomena.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p812},
read = {Yes},
rating = {2}
}

@article{gillen_contact_2013,
author = {Julia Gillen and Guy Merchant}, 
journal = {Language Sciences},
title = {Contact Calls: Twitter as a Dialogic Social and Linguistic Practice},
abstract = {The rapid adoption of new forms of digital communication is now attracting the attention of researchers from a wide range of disciplines in the social sciences. In the landscape of social media, the microblogging application Twitter has rapidly become an accepted fea- ture of everyday life with a broad appeal. This paper, from a dual autoethnography (Davies and Merchant, 2007) over one year, is a reflexive account of the experience of two aca- demic Twitter users. We offer analyses of the functionalities of the semiotic environment and trace how our meaning making practices illuminate Bakhtinian (1986) principles of human communication, while at the same time constituting literacies that are distinctively new in character. We show how communication using Web 2.0 technologies can be described as semiotic and sociolinguistic practice and offer an appropriately dialogic and exploratory methodology to the study of New Literacies.},
pages = {47--58},
volume = {35},
year = {2013},
keywords = {Bakhtin, Literacies, Twitter, New Literacy Studies, New Literacies, Dialogue}, 
date-added = {2013-04-13 21:02:22 +0100},
date-modified = {2013-06-11 10:06:17 +0100},
URL = {http://www.sciencedirect.com/science/article/pii/S0388000112000642},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2013/Gillen/Contact%20Calls%20Twitter%20as%20a%20Dialogic%20Social%20and%20Linguistic%20Practice.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p30608},
rating = {0}
}

@article{Byun:2012p30600,
author = {C Byun and Y Kim and H Lee and K Kim}, 
journal = {{\ldots} of the 14th International Conference on {\ldots}},
title = {Automated Twitter data collecting tool and case study with rule-based analysis},
abstract = {Applying data mining techniques to social media can yield interesting perspectives about individual human behavior, detecting hot issues and topics, or discovering a group and community. However, it is difficult to build your own data set to apply data mining techniques without an automated data gathering and filtering system because of main characteristics of social media: the data is large, noisy and dynamic. To overcome these challenges, we developed a java-based data gathering tool that continually collects social data from Twitter and filters noisy data. This allows us, as well as other researchers, to build our own Twitter database. In this paper, we introduce the design specifications and explain the implementation details of the Twitter Data Collecting Tool we developed. In addition, we provide an analysis of Twitter messages about various Super Bowl ads by applying data-mining techniques to a case study.},
year = {2012},
month = {Jan},
date-added = {2013-04-11 15:15:10 +0100},
date-modified = {2013-06-11 15:48:42 +0100},
pmid = {related:gmAymiYU0tsJ},
URL = {http://dl.acm.org/citation.cfm?id=2428768},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2012/Byun/Automated%20Twitter%20data%20collecting%20tool%20and%20case%20study%20with%20rule-based.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p30600},
rating = {0}
}

@article{An:2011p16066,
author = {J An and M Cha and K Gummadi and J Crowcroft}, 
title = {Media landscape in Twitter: A world of new conventions and political diversity},
abstract = {We present a preliminary but groundbreaking study of the media landscape of Twitter. We use public data on whom follows who to uncover common behaviour in media consumption, the relationship between vari- ous classes of media, and the diversity of media content which social links may bring. Our analysis shows that there is a non-negligible amount of indirect media expo- sure, either through friends who follow particular media sources, or via retweeted messages. We show that the indirect media exposure expands the political diversity of news to which users are exposed to a surprising ex- tent, increasing the range by between 60-98%. These results are valuable because they have not been readily available to traditional media, and they can help predict how we will read news, and how publishers will interact with us in the future.},
year = {2011},
date-added = {2011-04-11 22:51:45 +0100},
date-modified = {2012-04-18 14:10:02 +0100},
pmid = {related:qRiSKbsqesgJ},
URL = {www.cl.cam.ac.uk/~jac22/out/twitter-diverse.pdf},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/An/Media%20landscape%20in%20Twitter%20A.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p16066},
read = {Yes},
rating = {0}
}

@article{Yang:2012p29840,
author = {X Yang and A Ghoting and Y Ruan and S Parthasarathy}, 
title = {A framework for summarizing and analyzing twitter feeds},
abstract = {The firehose of data generated by users on social network- ing and microblogging sites such as Facebook and Twitter is enormous. Real-time analytics on such data is challenging with most current efforts largely focusing on the efficient querying and retrieval of data produced recently. In this paper, we present a dynamic pattern driven approach to summarize data produced by Twitter feeds. We develop a novel approach to maintain an in-memory summary while retaining sufficient information to facilitate a range of user- specific and topic-specific temporal analytics. We empir- ically compare our approach with several state-of-the-art pattern summarization approaches along the axes of storage cost, query accuracy, query flexibility, and efficiency using real data from Twitter. We find that the proposed approach is not only scalable but also outperforms existing approaches by a large margin.},
pages = {370--378},
year = {2012},
date-added = {2012-10-26 12:49:49 +0100},
date-modified = {2013-01-01 13:36:52 +0000},
pmid = {related:I2PaHQSWixwJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2012/Yang/A%20framework%20for%20summarizing%20and%20analyzing%20twitter%20feeds.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p29840},
rating = {0}
}

@article{Frahm:2012p29816,
author = {K.M Frahm and D.L Shepelyansky}, 
journal = {arXiv preprint arXiv:1207.3414},
title = {Google matrix of Twitter},
abstract = {We construct the Google matrix of the entire Twitter network, dated by July 2009, and analyze its spectrum and eigenstate properties including the PageRank and CheiRank vectors and 2DRanking of all nodes. Our studies show much stronger inter-connectivity between top PageRank nodes for the Twitter network compared to the networks of Wikipedia and British Universities studied previously. Our analysis allows to locate the top Twitter users which control the information flow on the network. We argue that this small fraction of the whole number of users, which can be viewed as the social network elite, plays the dominant role in the process of opinion formation on the network.},
year = {2012},
date-added = {2012-10-26 12:49:48 +0100},
date-modified = {2012-11-03 14:34:49 +0000},
pmid = {related:i_v2DO6OywsJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2012/Frahm/Google%20matrix%20of%20Twitter.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p29816},
rating = {0}
}

@article{Jansen:2011p1180,
author = {BJ Jansen and M Zhang and K Sobel and A Chowdury}, 
title = {The Commercial Impact of Social Mediating Technologies: Micro-blogging as Online Word-of-Mouth Branding},
abstract = {In this paper, we report research results investigating micro- blogging as a form of online word of mouth branding. We analyzed 149,472 micro-blog postings containing branding comments, sentiments, and opinions. We investigated the overall structure of these micro-blog postings and movement in positive or negative sentiment. We compared automated methods of classifying brand sentiment in these micro-blogs with manual coding. Our research findings show that 80 percent of micro-blogs containing branding comments were information seeking or sharing. Nearly 20 percent contained some expression of branding sentiments. Of these, more than 50 percent were positive and 33 percent were critical of the company or product. Our comparison of automated and manual coding showed no significant different between the two approaches. We discuss the implications of corporations in using micro-blogging as part of their overall marketing strategy and branding campaigns.},
year = {2011},
keywords = {sa, WOM}, 
date-added = {2010-10-31 22:01:12 +0000},
date-modified = {2012-04-18 14:09:55 +0100},
pmid = {related:nD_tk0lrtOwJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Jansen/The%20Commercial%20Impact%20of%20Social%20Mediating%20Technologies%20Micro-blogging%20as%20Online.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p1180},
read = {Yes},
rating = {4}
}

@article{Ceron:2013p30744,
author = {A Ceron and L Curini and S Iacus and G Porro}, 
journal = {New Media {\&} Society},
title = {Every tweet counts? How sentiment analysis of social media can improve our knowledge of citizens' political preferences with an application to Italy and France},
abstract = {The growing usage of social media by a wider audience of citizens sharply increases the possibility of investigating the web as a device to explore and track political preferences. In the present paper we apply a method recently proposed by other social scientists to three different scenarios, by analyzing on one side the online popularity of Italian political leaders throughout 2011, and on the other the voting intention of French Internet users in both the 2012 presidential ballot and the subsequent legislative election. While Internet users are not necessarily representative of the whole population of a country's citizens, our analysis shows a remarkable ability for social media to forecast electoral results, as well as a noteworthy correlation between social media and the results of traditional mass surveys. We also illustrate that the predictive ability of social media analysis strengthens as the number of citizens expressing their opinion online increases, provided that the citizens act consistently on these opinions.},
year = {2013},
month = {Jan},
date-added = {2013-04-18 09:56:42 +0100},
date-modified = {2013-04-18 09:56:56 +0100},
URL = {http://nms.sagepub.com/content/early/2013/04/02/1461444813480466.abstract},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2013/Ceron/Every%20tweet%20counts?%20How%20sentiment%20analysis%20of%20social%20media%20can.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p30744},
rating = {0}
}

@article{Brennan:2013p24325,
author = {M Brennan and R Greenstadt}, 
journal = {cs.drexel.edu},
title = {Coalescing Twitter Trends: The Under-Utilization of Machine Learning in Social Media},
abstract = {We demonstrate the effectiveness that machine learning can bring to improving social media platforms through a case study on Twitter trending topics. Social media relies heavily on tagging and often does not take advantage of machine learning advances. Twitter is no exception. Individual tweets are identified as being part of a trending discussion topic by the presence of a tagged keyword. Relying solely on this keyword, however, may be inadequate for identifying all the discussion associated with a trend. Our research demonstrates that machine learning techniques can be used identify the top trend a tweet belongs to with up to 85% precision without using the identifying keyword as a feature. This can aid in improving the quality of topic categorization by ensuring on-topic tweets that are missing the trend keyword are included, as well as suggest keywords to include in new tweets.},
date-added = {2011-10-27 23:15:53 +0100},
date-modified = {2012-04-18 14:09:24 +0100},
URL = {https://www.cs.drexel.edu/~mb553/stuff/brennan_socialcom.pdf},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/Unknown/Brennan/Coalescing%20Twitter%20Trends%20The%20Under-Utilization%20of%20Machine%20Learning%20in%20Social.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p24325},
rating = {0}
}

@article{potts_contextualizing_2011,
author = {Liza Potts and Dave Jones}, 
journal = {Journal of Business and Technical Communication},
title = {Contextualizing experiences: Tracing the relationships between people and technologies in the social web},
abstract = {This article uses both actor network theory (ANT) and activity theory to trace and analyze the ways in which both Twitter and third-party applications support the development and maintenance of meaningful contexts for Twitter participants. After situating context within the notion of a ''fire space'', the authors use ANT to trace the actors that support finding and moving information. Then they analyze the ''prescriptions'' of each application using the activity-theory distinction between actions and operations. Finally, they combine an activity-theory analysis with heuristics derived from the concept of ''findability'' in order to explore design implications for Social Web applications.},
note = {Journal Article},
number = {3},
pages = {338--358},
volume = {25},
year = {2011},
keywords = {Business And Economics}, 
date-added = {2013-04-13 21:02:21 +0100},
date-modified = {2013-04-13 21:02:22 +0100},
URL = {http://dx.doi.org/10.1177/1050651911400839},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Potts/Contextualizing%20experiences%20Tracing%20the%20relationships%20between%20people%20and%20technologies%20in.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p30625},
rating = {0}
}

@article{Wandhofer:2012p30824,
author = {Timo Wandh{\"o}fer and Steve Taylor and Paul Walland and Ruxandra Geana and Robert Weichselbaum and Miriam Fernandez and Sergej Sizov}, 
journal = {eJournal of eDemocracy {\&} Open Government (JeDEM)},
title = {Determining citizens' opinions about stories in the news media: analysing Google, Facebook and Twitter},
abstract = {We describe a method whereby a governmental policy maker can discover citizens' reaction to news stories. This is particularly relevant in the political world, where governments' policy statements are reported by the news media and discussed by citizens. The work here addresses two main questions: whereabouts are citizens discussing a news story, and what are they saying? Our strategy to answer the first question is to find news articles pertaining to the policy statements, and then perform internet searches for references to the news articles' headlines and URLs. We have created a software tool that schedules repeating Google searches for the news articles and collects the results in a database, enabling the user to aggregate and analyse them to produce ranked tables of sites that reference the news articles. Using data mining techniques we can analyse data so that resultant ranking reflects an overall aggregate score, taking into account multiple datasets, and this shows the most relevant places on the internet where the story is discussed. To answer the second question, we introduce the WeGov toolbox as a tool for analysing citizens' comments and behaviour pertaining to news stories. We first use the tool for identifying social network discussions, using different strategies for Facebook and Twitter. We apply different analysis components to analyse the data to distil the essence of the social network users' comments, to determine influential users and identify important comments.},
number = {2},
pages = {198--221},
volume = {4},
year = {2012},
date-added = {2013-04-25 14:52:00 +0100},
date-modified = {2013-06-11 11:52:02 +0100},
pmid = {related:kDgyZt_nP7EJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2012/Wandh%C3%B6fer/Determining%20citizens%E2%80%99%20opinions%20about%20stories%20in%20the%20news%20media%20analysing.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p30824},
rating = {0}
}

@article{Hochman:2012p30013,
author = {N Hochman and R Schwartz}, 
title = {Visualizing Instagram: Tracing Cultural Visual Rhythms},
abstract = {Picture-taking has never been easier. We now use our phones to snap photos and instantly share them with friends, fam- ily and strangers all around the world. Consequently, we seek ways to visualize, analyze and discover concealed socio- cultural characteristics and trends in this ever-growing flow of visual information. How do we then trace global and lo- cal patterns from the analysis of visual planetary--scale data? What types of insights can we draw from the study of these massive visual materials? In this study we use Cultural Ana- lytics visualization techniques for the study of approximately 550,000 images taken by users of the location-based social photo sharing application Instagram. By analyzing images from New York City and Tokyo, we offer a comparative vi- sualization research that indicates differences in local color usage, cultural production rate, and varied hue's intensities--- all form a unique, local, `Visual Rhythm': a framework for the analysis of location-based visual information flows.},
year = {2012},
keywords = {AAAI Technical Report WS-12-03}, 
date-added = {2012-12-25 13:45:02 +0000},
date-modified = {2013-06-11 14:50:09 +0100},
pmid = {related:62RafYcr10EJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2012/Hochman/Visualizing%20Instagram%20Tracing%20Cultural%20Visual%20Rhythms.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p30013},
rating = {0}
}

@inproceedings{wu_who_2011,
author = {Shaomei Wu and Jake M Hofman and Winter A Mason and Duncan J Watts}, 
journal = {Proceedings},
title = {Who Says What to Whom on Twitter},
abstract = {We study several longstanding questions in media communi- cations research, in the context of the microblogging service Twitter, regarding the production, flow, and consumption of information. To do so, we exploit a recently introduced fea- ture of Twitter known as ``lists'' to distinguish between elite users---by which we mean celebrities, bloggers, and represen- tatives of media outlets and other formal organizations---and ordinary users. Based on this classification, we find a strik- ing concentration of attention on Twitter, in that roughly 50% of URLs consumed are generated by just 20K elite users, where the media produces the most information, but celebrities are the most followed. We also find significant homophily within categories: celebrities listen to celebrities, while bloggers listen to bloggers etc; however, bloggers in general rebroadcast more information than the other cate- gories. Next we re-examine the classical ``two-step flow'' the- ory of communications, finding considerable support for it on Twitter. Third, we find that URLs broadcast by different categories of users or containing different types of content exhibit systematically different lifespans. And finally, we ex- amine the attention paid by the different user categories to different news topics.},
affiliation = {Hyderabad, India},
pages = {705--714},
year = {2011},
date-added = {2013-04-13 21:02:22 +0100},
date-modified = {2013-06-11 11:23:26 +0100},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Wu/Who%20Says%20What%20to%20Whom%20on%20Twitter.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p30604},
rating = {0}
}

@article{Asur:2010p850,
author = {S Asur and BA Huberman}, 
title = {Predicting the future with social media},
abstract = {In recent years, social media has become ubiquitous and important for social networking and content sharing. And yet, the content that is generated from these websites remains largely untapped. In this paper, we demonstrate how social media content can be used to predict real-world outcomes. In particular, we use the chatter from Twitter.com to forecast box-office revenues for movies. We show that a simple model built from the rate at which tweets are created about particular topics can outperform market-based predictors. We further demonstrate how sentiments extracted from Twitter can be further utilized to improve the forecasting power of social media.},
year = {2010},
keywords = {movie}, 
date-added = {2010-10-30 18:30:53 +0100},
date-modified = {2012-04-18 14:10:42 +0100},
pmid = {9454329878348062305related:YV5M5O6GNIMJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2010/Asur/Predicting%20the%20future%20with%20social.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p850},
read = {Yes},
rating = {4}
}

@article{Wu:2010p1712,
author = {W Wu and B Zhang and M Ostendorf}, 
journal = {Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics},
title = {Automatic generation of personalized annotation tags for Twitter users},
abstract = {This paper introduces a system designed for automatically generating personalized annotation tags to label Twitter user's interests and concerns. We applied TFIDF ranking and TextRank to extract keywords from Twitter messages to tag the user. The user tagging precision we obtained is comparable to the precision of keyword extraction from web pages for content-targeted advertising.},
pages = {689--692},
year = {2010},
date-added = {2010-11-04 09:59:28 +0000},
date-modified = {2012-04-18 14:09:43 +0100},
pmid = {related:rq57UxJdSWAJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2010/Wu/Automatic%20generation%20of%20personalized%20annotation%20tags%20for%20Twitter%20users.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p1712},
read = {Yes},
rating = {0}
}

@article{Kato:2012p29796,
author = {S Kato and A Koide and T Fushimi and K Saito and H Motoda}, 
journal = {Knowledge Management and Acquisition for Intelligent Systems},
title = {Network Analysis of Three Twitter Functions: Favorite, Follow and Mention},
abstract = {We analyzed three functions of Twitter (Favorite, Followand Mention) from network structural point of view. These three functions are characterized by difference and similarity in various measures de- fined in directed graphs. Favorite function can be viewed by three differ- ent graph representations: a simple graph, a multigraph and a bipartite graph, Follow function by one graph representation: a simple graph, and Mention function by two graph representations: a simple graph and a multigraph. We created these graphs from three real world twitter data and found salient features characterizing these functions. Major findings are a very large connected component for Favorite and Follow functions, scale-free property in degree distribution and predominant mutual links in certain network motifs for all three functions, freaks in Gini coefficient and two clusters of popular users for Favorites function, and a structure difference in high degree nodes between Favorite and Mention functions characterizing that Favorite operation is much easier than Mention op- eration. These finding will be useful in building a preference model of Twitter users.},
pages = {298--312},
year = {2012},
date-added = {2012-10-26 12:49:40 +0100},
date-modified = {2013-06-11 14:23:56 +0100},
pmid = {related:QnvtEP6LzVwJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2012/Kato/Network%20Analysis%20of%20Three%20Twitter%20Functions%20Favorite%20Follow%20and%20Mention.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p29796},
rating = {0}
}

@article{Oliveira:2013p31273,
author = {N Oliveira and P Cortez and N Areal}, 
journal = {WIMS'13},
title = {Some experiments on modeling stock market behavior using investor sentiment analysis and posting volume from Twitter},
abstract = {The analysis of microblogging data related with stock markets can reveal relevant new signals of investor sentiment and attention. It may also provide sentiment and attention indicators in a more rapid and cost-effective manner than other sources. In this study, we created several indicators using Twitter data and investigated their value when model- ing relevant stock market variables, namely returns, trading volume and volatility. We collected recent data from nine ma jor technological companies. Several sentiment analysis methods were explored, by comparing 5 popular lexical resources and two novel lexicons (emoticon based and the merge of all 6 lexicons) and sentiment indicators produced using two strategies (based on daily words and individual tweet classifications). Also, we measured posting volume associated with tweets related to the analyzed companies. While a short time period is considered (32 days), we found scarce evidence that sentiment indicators can explain these stock returns. However, interesting results were obtained when measuring the value of using posting volume for fitting trading volume and, in particular, volatility.},
year = {2013},
month = {Dec},
date-added = {2013-06-18 15:09:53 +0100},
date-modified = {2013-07-08 11:16:11 +0100},
URL = {http://dl.acm.org/citation.cfm?id=2479811},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2013/Oliveira/Some%20experiments%20on%20modeling%20stock%20market%20behavior%20using%20investor%20sentiment.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p31273},
read = {Yes},
rating = {0}
}

@article{Abel:2011p28832,
author = {F Abel and Q Gao and G Houben and K Tao}, 
journal = {citeulike.org
},
title = {Analyzing User Modeling on Twitter for Personalized News Recommendations},
abstract = {How can micro-blogging activities on Twitter be leveraged for user modeling and personalization? In this paper we investigate this question and introduce a framework for user modeling on Twitter which enriches the semantics of Twitter messages (tweets) and identifies topics and entities (e.g. persons, events, products) mentioned in tweets. We analyze how strategies for constructing hashtag-based, entity-based or topic-based user profiles benefit from semantic enrichment and explore the temporal dynamics of those profiles. We further measure and com- pare the performance of the user modeling strategies in context of a personalized news recommendation system. Our results reveal how se- mantic enrichment enhances the variety and quality of the generated user profiles. Further, we see how the different user modeling strategies impact personalization and discover that the consideration of temporal profile patterns can improve recommendation quality.},
year = {2011},
month = {Jan},
date-added = {2012-09-30 22:05:05 +0100},
date-modified = {2013-06-11 16:17:34 +0100},
URL = {http://www.citeulike.org/group/2072/article/9547638},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Abel/Analyzing%20User%20Modeling%20on%20Twitter%20for%20Personalized%20News%20Recommendations-1.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p28832},
rating = {0}
}

@article{Ou:2011p21139,
author = {C Ou and RM Davison and N Cheng}, 
journal = {projects.business.uq.edu.au},
title = {WHY ARE SOCIAL NETWORKING APPLICATIONS SUCCESSFUL? AN EMPIRICAL STUDY OF TWITTER},
abstract = {Social networking applications (SNAs) are among the fastest growing web applications of recent years. In this paper, we propose a causal model to assess the success of SNAs, grounded on DeLone and McLean's updated information system (IS) success model. In addition to their original three dimensions of quality, i.e., system quality, information quality and service quality, we propose that a fourth dimension -- networking quality -- contributes to SNA success. We empirically examined the proposed research model with a survey of 139 Twitter users. The data validates the significant role of networking quality in determining the focal SNA's success. This study also highlights the overwhelming impact of networking quality on user satisfaction compared to the influence from information quality and service quality. The theoretical and practical implications are discussed.},
year = {2011},
date-added = {2011-07-12 12:53:52 +0100},
date-modified = {2012-04-18 14:10:39 +0100},
URL = {http://projects.business.uq.edu.au/pacis2011/papers/PACIS2011-141.pdf},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Ou/WHY%20ARE%20SOCIAL%20NETWORKING%20APPLICATIONS%20SUCCESSFUL?%20AN%20EMPIRICAL%20STUDY%20OF.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p21139},
rating = {0}
}

@article{Owoputi:2013p31156,
author = {O Owoputi and B O'Connor and C Dyer and K Gimpel and N Shneider and N.A Smith}, 
journal = {Proceedings of NAACL- {\ldots}},
title = {Improved part-of-speech tagging for online conversational text with word clusters},
abstract = {We consider the problem of part-of-speech tagging for informal, online conversational text. We systematically evaluate the use of large-scale unsupervised word clustering and new lexical features to improve tagging accuracy. With these features, our system achieves state-of-the-art tagging results on both Twitter and IRC POS tagging tasks; Twitter tagging is improved from 90% to 93% accuracy (more than 3% absolute). Quali- tative analysis of these word clusters yields insights about NLP and linguistic phenomena in this genre. Additionally, we contribute the first POS annotation guidelines for such text and release a new dataset of English language tweets annotated using these guidelines. Tagging software, annotation guidelines, and large-scale word clusters are available at: http://www.ark.cs.cmu.edu/TweetNLP This paper describes release 0.3 of the ``CMU Twitter Part-of-Speech Tagger'' and annotated data.},
year = {2013},
month = {Jan},
date-added = {2013-06-04 17:51:32 +0100},
date-modified = {2013-06-11 10:00:30 +0100},
pmid = {1899427335040502113},
URL = {http://www.aclweb.org/anthology/N/N13/N13-1039.pdf},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2013/Owoputi/Improved%20part-of-speech%20tagging%20for%20online%20conversational%20text%20with%20word%20clusters.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p31156},
rating = {0}
}

@article{Li:2011p19866,
author = {Z Li}, 
journal = {Retrieved on},
title = {Knowledge Discovery from Twitter},
abstract = {Microblogging services like Twitter [1] are more and more popular, forming as a part of social media, social network and communication tool. Currently the number of microblogging entries in Twitter, known as tweets, is quite big and still increasing every day. Information management and organization in microblog are becoming not only a problem, but also an interesting research topic. The huge amount of text data produced by Twitter becomes a very desirable dataset for knowledge mining and discovery. Besides utilizing the text of tweets data, the users in Twitter are connected by "following" relationship (i.e. feeding someone's tweets by "following" him), we can then build a text-associated information network for better modeling and interesting patterns discovery over text data. This paper is basically going to achieve three research tasks over Twitter data: tweets filtering based on a user's interests, community discovery in a large group of people, and tweets classification. Generally, identifying interests helps filtering undesirable information on incoming tweets, community discovery helps find subgroups of certain interests and suggest users who have similar interests to follow, and tweets classification helps user choose his favorite categories of tweets to read. Experiments are designed and performed respectively. The experimental results show the effectiveness of proposed statistical framework and algorithms for these tasks.},
volume = {5},
year = {2011},
date-added = {2011-06-13 14:02:24 +0100},
date-modified = {2012-04-18 14:09:13 +0100},
pmid = {17738351531875369344related:gAFwhrxIK_YJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Li/Knowledge%20Discovery%20from%20Twitter.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p19866},
rating = {0}
}

@article{Hogan:2010p30417,
author = {B Hogan and A Quan-Haase}, 
journal = {Bulletin of Science, Technology {\&} Society},
title = {Persistence and Change in Social Media},
number = {5},
pages = {309--315},
volume = {30},
year = {2010},
month = {Oct},
date-added = {2013-01-17 11:13:30 +0000},
date-modified = {2013-01-17 11:13:30 +0000},
doi = {10.1177/0270467610380012},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2010/Hogan/Persistence%20and%20Change%20in%20Social%20Media.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p30417},
rating = {0}
}

@article{Bermingham:2010p1791,
author = {A Bermingham and A F Smeaton}, 
title = {Crowdsourced real-world sensing: sentiment analysis and the real-time web},
abstract = {The advent of the real-time web is proving both challenging and at the same time disruptive for a number of areas of research, notably information retrieval and web data mining. As an area of re- search reaching maturity, sentiment analysis offers a promising direction for modelling the text content available in real-time streams. This paper reviews the real-time web as a new area of focus for sentiment analysis and discusses the motivations and challenges behind such a direction.},
year = {2010},
month = {Jan},
keywords = {sa}, 
date-added = {2010-11-04 10:13:00 +0000},
date-modified = {2012-04-18 14:10:06 +0100},
pmid = {related:2scGtWeBaicJ},
URL = {http://doras.dcu.ie/15585/},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2010/Bermingham/Crowdsourced%20real-world%20sensing%20sentiment%20analysis.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p1791},
read = {Yes},
rating = {3}
}

@article{Kwon:2011p21405,
author = {E Kwon}, 
journal = {repositories.lib.utexas.edu},
title = {Follow me! I will be your best friend: global marketers' Twitter use},
abstract = {Social media have grown into a powerful marketing communications tool in the global market. A number of companies are dedicating their time and resources for building trust and rapport with consumers through various social media platforms, but there is a dearth of research on their use of Twitter. The current study, therefore, examines global brands with a Twitter account and their tweets targeted at consumers. The results indicate that marketers attempt to attribute human characteristics to their brands using human representatives, personal pronouns, verbs in the imperative form. Also, satisfaction and investment were the most frequently found consumer-brand relationship determinants in the global brands' tweets. This study offers the perspective that Twitter serves not only as an optimal vehicle for disseminating corporate information but also as a means to develop and cultivate consumer-brand relationships. Limitations and future research are discussed.},
year = {2011},
month = {Jan},
date-added = {2011-07-30 21:53:31 +0100},
date-modified = {2012-04-18 14:10:01 +0100},
URL = {http://repositories.lib.utexas.edu/handle/2152/12380},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Kwon/Follow%20me!%20I%20will%20be%20your%20best%20friend%20global%20marketers'.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p21405},
rating = {0}
}

@article{Crowston:2010p30612,
author = {Kevin Crowston and Eileen Allen and Robert Heckman and Michael J Scialdone and Robert Heckman}, 
journal = {International Journal of Social Research Methodology},
title = {Using natural language processing technology for qualitative data analysis},
abstract = {Social researchers often apply qualitative research methods to study groups and their communications artefacts. The use of computer-mediated communications has dramatically increased the volume of text available, but coding such text requires considerable manual effort. We discuss how systems that process text in human languages (i.e., natural language processing, NLP) might partially automate content analysis by extracting theoretical evidence. We present a case study of the use of NLP for qualitative analysis in which the NLP rules showed good performance on a number of codes. With the current level of performance, use of an NLP system could reduce the amount of text to be examined by a human coder by an order of magnitude or more, potentially increasing the speed of coding by a comparable degree. The paper is significant as it is one of the first to demonstrate the use of high-level NLP techniques for qualitative data analysis.},
number = {6},
pages = {523--543},
volume = {15},
year = {2010},
date-added = {2013-04-13 21:02:22 +0100},
date-modified = {2013-06-11 15:35:31 +0100},
pmid = {related:ASSs8KyrIjYJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2010/Crowston/Using%20natural%20language%20processing%20technology%20for%20qualitative%20data%20analysis.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p30612},
rating = {0}
}

@article{Buzeck:2010p14481,
author = {M Buzeck and J Muller}, 
journal = {MM'10},
title = {TwitterSigns: Microblogging on the walls},
abstract = {In this paper we present TwitterSigns, an approach to display microblogs on public displays. Two different kinds of microblog entries (tweets) are selected for display: Tweets that were posted in the immediate environment of the display, and tweets that were posted by people associated with the location where the displays are installed (locals). The prototype was tested in a university setting on 4 displays for 4 weeks and compared to the information system that is usually running on the displays (iDisplays). Using face detection we show that people look significantly longer at TwitterSigns than at iDisplays. Interviews show that the relationship of viewer and poster as well as the tweet content are much more important than time and location of the tweet. Viewers recall and recognize mostly tweets from peo- ple they know, and of apparent importance for themselves (like a apparent bomb found in the city center). Furthermore, TwitterSigns change the way people use twitter (e.g. they feel more responsible for what they tweet). Passers-by seem only to look for keywords and only stop and read the whole tweet if they found some interesting keyword.},
year = {2010},
month = {Jan},
date-added = {2011-03-14 20:51:12 +0000},
date-modified = {2013-06-11 15:49:34 +0100},
pmid = {related:U9kDRxT7nsQJ},
URL = {http://portal.acm.org/citation.cfm?id=1874087},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2010/Buzeck/TwitterSigns%20Microblogging%20on%20the%20walls.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p14481},
read = {Yes},
rating = {0}
}

@article{Cogan:2012p29800,
author = {P Cogan and M Andrews and M Bradonjic and G Tucci and W.S Kennedy and A Sala}, 
title = {Reconstruction and Analysis of Twitter Conversation Graphs},
abstract = {User interactions over social networks has been an emergent theme over the last several years. In contrast to previous work we focus on characterizing user communications pat- terns around an initial post, or conversation root. Specif- ically, we focus on how other users respond to these roots and how the complete conversation initiated by this root evolves over time. For this purpose we focus our investi- gation on Twitter, the biggest micro-blogging social net- work. To the best of our knowledge this is the first such method that is able to reconstruct complete conversations around initial tweets. We propose a robust approach for reconstructing complete conversations and compare the re- sulting graph structures against those obtained from pre- vious crawling strategies based on keyword searches. Our crawl provides a large scale dataset, ideal for computer sci- entists to run large scale experimental evaluations, however our dataset is made of a collection of small scale, highly controlled and complete conversation graphs ideal for a so- ciological investigation. We believe our work will provide the proper dataset to establish concrete collaborations with interdisciplinary expertise.},
year = {2012},
date-added = {2012-10-26 12:49:49 +0100},
date-modified = {2013-06-11 15:35:49 +0100},
pmid = {related:GYyodHFyEW0J},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2012/Cogan/Reconstruction%20and%20Analysis%20of%20Twitter%20Conversation%20Graphs.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p29800},
rating = {0}
}

@article{Suh:2010p27416,
author = {B Suh and L Hong and P Pirolli and E.H Chi}, 
journal = {Social Computing (SocialCom), 2010 IEEE Second International Conference on},
title = {Want to be retweeted? Large scale analytics on factors impacting retweet in Twitter network},
pages = {177--184},
year = {2010},
date-added = {2012-02-24 21:42:18 +0000},
date-modified = {2012-04-18 14:09:45 +0100},
pmid = {4176598563614687069related:Xf-o2UNC9jkJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2010/Suh/Want%20to%20be%20retweeted?%20Large.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p27416},
rating = {0}
}

@article{Dean:2011p24323,
author = {J Dean}, 
journal = {University of Cincinnati Law Review},
title = {TO TWEET OR NOT TO TWEET: TWITTER, ``BROADCASTING,'' AND FEDERAL RULE OF CRIMINAL PROCEDURE 53},
number = {2},
pages = {1--23},
volume = {79},
year = {2011},
month = {Oct},
date-added = {2011-10-27 09:12:08 +0100},
date-modified = {2013-06-11 15:24:17 +0100},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Dean/TO%20TWEET%20OR%20NOT%20TO%20TWEET%20TWITTER%20%E2%80%9CBROADCASTING%E2%80%9D%20AND%20FEDERAL.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p24323},
rating = {0}
}

@article{Paul:2011p17128,
author = {MJ Paul and Mark Dredze}, 
journal = {HEALTH},
title = {A Model for Mining Public Health Topics from Twitter},
abstract = {We present the Ailment Topic Aspect Model (ATAM), a new topic model for Twitter that associates symptoms, treatments and general words with diseases (ailments).  We train ATAM on a new collection of 1.6 million tweets discussing numerous health related topics. ATAM isolates more coherent ail- ments, such as influenza, infections, obesity, as compared to standard topic models. Fur- thermore, ATAM matches influenza tracking results produced by Google Flu Trends and previous influenza specialized Twitter models compared with government public health data.},
year = {2011},
date-added = {2011-04-23 01:38:01 +0100},
date-modified = {2012-04-18 14:09:36 +0100},
pmid = {9148093166228836284},
URL = {http://www.cs.jhu.edu/~mpaul/files/2011.tech.twitter_health.pdf},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Paul/A%20Model%20for%20Mining%20Public.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p17128},
rating = {0}
}

@article{GonzalezIbanez:2011p25577,
author = {R Gonz{\'a}lez-Ib{\'a}{\~n}ez and S Muresan and N Wacholder}, 
journal = {Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies: short papers},
title = {Identifying sarcasm in Twitter: a closer look},
abstract = {arcasm transforms the polarity of an ap- parently positive or negative utterance into its opposite. We report on a method for constructing a corpus of sarcastic Twitter messages in which determination of the sarcasm of each message has been made by its author. We use this reliable corpus to compare sarcastic utterances in Twitter to utterances that express positive or negative attitudes without sarcasm. We investigate the impact of lexical and pragmatic factors on machine learning effectiveness for iden- tifying sarcastic utterances and we compare the performance of machine learning tech- niques and human judges on this task. Per- haps unsurprisingly, neither the human judges nor the machine learning techniques perform very well.},
pages = {581--586},
volume = {2},
year = {2011},
date-added = {2012-01-01 20:42:24 +0000},
date-modified = {2012-04-18 14:10:39 +0100},
pmid = {related:RABAegYleLgJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Gonz%C3%A1lez-Ib%C3%A1%C3%B1ez/Identifying%20sarcasm%20in%20Twitter%20a.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p25577},
read = {Yes},
rating = {0}
}

@article{Ritterman:2009p6,
author = {J Ritterman and M Osborne and E Klein}, 
journal = {1st International Workshop on Mining Social Media},
title = {Using prediction markets and Twitter to predict a swine flu pandemic},
abstract = {We explore the hypothesis that social media such as Twitter encodes the belief of a large number of people about some concrete statement about the world. Here, these beliefs are aggregated using a Prediction Market specifically concerning the possibility of a Swine Flu Pandemic in 2009. Using a regression framework, we are able to show that simple features extracted from Tweets can reduce the error associated with modelling these beliefs. Our approach is also shown to outperform some baseline methods based purely on time-series information from the Market.},
year = {2009},
date-added = {2010-10-26 19:53:26 +0100},
date-modified = {2012-04-18 14:10:55 +0100},
pmid = {7391319559368903509related:VYuUdfo9k2YJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2009/Ritterman/Using%20prediction%20markets%20and%20Twitter%20to%20predict%20a%20swine%20flu.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p6},
read = {Yes},
rating = {4}
}

@article{LOTAN:2011p25562,
author = {G LOTAN and E GRAEFF and M ANANNY and D GAFFNEY and I Pearce and D BOYD}, 
journal = {International Journal of Communication},
title = {The Revolutions Were Tweeted: Information Flows During the 2011 Tunisian and Egyptian Revolutions},
abstract = {This article details the networked production and dissemination of news on Twitter during snapshots of the 2011 Tunisian and Egyptian Revolutions as seen through information flows---sets of near-duplicate tweets---across activists, bloggers, journalists, mainstream media outlets, and other engaged participants. We differentiate between these user types and analyze patterns of sourcing and routing information among them. We describe the symbiotic relationship between media outlets and individuals and the distinct roles particular user types appear to play. Using this analysis, we discuss how Twitter plays a key role in amplifying and spreading timely information across the globe.},
pages = {1375--1405},
volume = {5},
year = {2011},
date-added = {2011-12-23 12:22:53 +0000},
date-modified = {2012-04-18 14:09:25 +0100},
doi = {1932–8036/2011FEA1375},
pmid = {related:OfD3ePevAqYJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/LOTAN/The%20Revolutions%20Were%20Tweeted%20Information%20Flows%20During%20the%202011%20Tunisian.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p25562},
rating = {0}
}

@article{Kwak:2011p22216,
author = {H Kwak and C Lee and H Park and H Chun and S Moon}, 
journal = {ACM SIGWEB Newsletter},
title = {Novel aspects coming from the directionality of online relationships: a case study of Twitter},
abstract = {In the past decade online social networking services, such as Myspace and Facebook, have dra- matically changed how we spend time online, stay connected with friends and search for infor- mation. All the activities are based on online relationships called 'friends'. These relationships are commonly bidirectional; one requests and the other accepts. Not all online relationships are bidirectional. The online relationship in Twitter, known as follow, is directed. People can follow any other person without an approval. In this article we show novel aspects of Twitter that come from the directionality in relationships: topological characteristics of the directed network, word- of-mouth information spreading via retweet, and online relationship dissolution. We wrap up the article with future directions in our information diffusion study.},
number = {Summer},
pages = {5},
year = {2011},
date-added = {2011-08-15 07:59:08 +0100},
date-modified = {2013-06-11 14:19:01 +0100},
pmid = {related:kB_CsLaLAd4J},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Kwak/Novel%20aspects%20coming%20from%20the%20directionality%20of%20online%20relationships%20a.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p22216},
rating = {0}
}

@article{Armentano:2010p20482,
author = {M Armentano and DL Godoy and A Amandi}, 
title = {A topology-based approach for followees recommendation in Twitter},
abstract = {Nowadays, more and more users keep up with news through information streams coming from real-time micro-blogging activity offered by services such as Twitter. In these sites, information is shared via a followers/followees social network structure in which a follower will receive all the micro-blogs from the users he follows, named followees. Recent research efforts on understanding micro-blogging as a novel form of communication and news spreading medium have identified different categories of users in Twitter: information sources, information seekers and friends. Users acting as information sources are characterized for having a larger number of followers than followees, information seekers subscribe to this kind of users but rarely post tweets and, finally, friends are users exhibiting reciprocal relationships. With in- formation seekers being an important portion of registered users in the system, finding relevant and reliable sources becomes essential. To address this problem, we propose a followee recommender system based on an algorithm that explores the topology of followers/followees network of Twitter considering different factors that allow us to identify users as good information sources. Experimental evaluation conducted with a group of users is reported, demonstrating the potential of the approach.},
year = {2010},
date-added = {2011-06-16 12:48:35 +0100},
date-modified = {2012-04-18 14:09:17 +0100},
URL = {http://ls13-www.cs.uni-dortmund.de/homepage/itwp2011/papers/manuscript-itwp11-camera-ready.pdf},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2010/Armentano/A%20topology-based%20approach%20for%20followees.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p20482},
rating = {0}
}

@article{Petrovic:2013p31149,
author = {S Petrovic and M Osborne and R McCreadie and C Macdonald and I Ounis and L Shrimpton}, 
journal = {homepages.inf.ed.ac.uk
},
title = {Can Twitter replace Newswire for breaking news?},
abstract = {Twitter is often considered to be a useful source of real-time
news, potentially replacing newswire for this purpose. But
is this true? In this paper, we examine the extent to which
news reporting in newswire and Twitter overlap and whether
Twitter often reports news faster than traditional newswire
providers. In particular, we analyse 77 days worth of tweet
and newswire articles with respect to both manually identified
major news events and larger volumes of automatically identified news events. Our results indicate that Twitter reports
the same events as newswire providers, in addition to a long
tail of minor events ignored by mainstream media. However,
contrary to popular belief, neither stream leads the other when
dealing with major news events, indicating that the value that
Twitter can bring in a news setting comes predominantly from
increased event coverage, not timeliness of reporting},
year = {2013},
month = {Jan},
date-added = {2013-06-04 17:37:16 +0100},
date-modified = {2013-06-11 09:56:18 +0100},
URL = {http://homepages.inf.ed.ac.uk/miles/papers/short-breaking.pdf},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2013/Petrovic/Can%20Twitter%20replace%20Newswire%20for%20breaking%20news?.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p31149},
rating = {0}
}

@article{Hsieh:2013p28812,
author = {C Hsieh and C Moghbel and J Fang and J Cho}, 
journal = {oak.cs.ucla.edu
},
title = {Experts vs The Crowd: Examining Popular News Prediction Perfomance on Twitter},
abstract = {In the finance domain, the famous Efficient Market Hypoth- esis(EMH) [9] concludes that crowd wisdom is superior to any expert wisdom in picking financial stocks. In this study, we test a similar hypothesis in the domain of news recom- mendation by conducting experiments on Twitter. We first identify a group of experts on Twitter who have consistently identified ``interesting'' (or popular) news early on and have recommended them in their tweets. We then collect two sets of news: a set of incoming news recommended by these ex- perts and a similar set recommended by the ``crowd''. We then observe, for a few months, how widely the news in the two sets are circulated on Twitter, and evaluate which set contains more widely-circulated news (and therefore are more likely to be interesting). After conducting repeated ex- periments, we draw a similar conclusion to the EMH -- the crowd wisdom is always the winner in our experiments; we could not identify an expert group whose news recommen- dation performance was consistently better than that of the crowd. We then proceed to investigate whether the expert wisdom can be used to improve crowd wisdom in any way.},
year = {2013},
month = {Jan},
date-added = {2012-09-30 21:14:42 +0100},
date-modified = {2013-06-11 10:01:16 +0100},
URL = {http://oak.cs.ucla.edu/~chucheng/publication/WSDM2013CNF.pdf},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2013/Hsieh/Experts%20vs%20The%20Crowd%20Examining%20Popular%20News%20Prediction%20Perfomance%20on.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p28812},
rating = {0}
}

@article{Ruiz:2012p30821,
author = {Eduardo Ruiz and Vagelis Hristidis and Carlos Castillo and Aristides Gionis and Alejandro Jaimes}, 
title = {Correlating financial time series with micro-blogging activity},
abstract = {We study the problem of correlating micro-blogging activity with stock-market events, defined as changes in the price and traded volume of stocks. Specifically, we collect messages related to a number of companies, and we search for correlations between stock-market events for those companies and features extracted from the micro-blogging messages. The features we extract can be categorized in two groups. Features in the first group measure the overall activity in the micro-blogging platform, such as number of posts, number of re-posts, and so on. Features in the second group measure properties of an induced interaction graph, for instance, the number of con- nected components, statistics on the degree distribution, and other graph-based properties.
We present detailed experimental results measuring the correlation of the stock market events with these features, using Twitter as a data source. Our results show that the most correlated features are the number of connected components and the number of nodes of the interaction graph. The correlation is stronger with the traded volume than with the price of the stock. However, by using a simulator we show that even relatively small correlations between price and micro-blogging features can be exploited to drive a stock trading strategy that outperforms other baseline strategies.},
pages = {513--522},
year = {2012},
date-added = {2013-04-25 14:17:52 +0100},
date-modified = {2013-07-08 11:11:12 +0100},
pmid = {5877339426796915860related:lMygthGBkFEJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2012/Ruiz/Correlating%20financial%20time%20series%20with%20micro-blogging%20activity.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p30821},
read = {Yes},
rating = {0}
}

@article{Jalbuena:2013p30963,
author = {M Jalbuena}, 
journal = {MSEUF Research Studies},
title = {Linguistic Features of English in Twitter},
abstract = {This paper looked into the tweets of five prominent personalities in each of the following fields - education, entertainment, social life, politics and personal level -and analyzed the tone as well as the typing styles embedded in the lexical, grammatical and rhetorical features of the tweets. The content words or lexical features of English used in the five categories of tweets studied were neutral number nouns, singulars and plurals and proper nouns; unmarked adverbs, adverb particles and wh- adverbs; unmarked adjectives, comparatives and superlatives; the base form of the verb ``be'', past form of the verb ``be'', -ing form of the verb ``be'', infinitive of the verb ``be'', past participle of the verb ``be'', -s form of the verb ``be'', base form of the verb ``do'', infinitive of the verb ``do'', infinitive form of the verb ``have'', base form of the lexical verb, past tense form of the lexical verb, -ing form of the lexical verb, infinitive of the lexical verb , past participle form of lexical verb and -s form of the lexical verb. Majority of the Twitter users from the five categories used lexical verbs followed by nouns, adjectives and adverbs in their tweets. The dominant grammatical features of English used in Twitter are prepositions; indefinite, personal, reflexive and wh-pronouns; auxiliary verbs, the base form of the verb ``be'', past form of the verb ``be'', -ing form of the verb ``be'', infinitive of the verb ``be'', past participle of the verb ``be'', -s form of the verb ``be'', base form of the verb ``do'', past form of the verb ``do, infinitive of the verb ``do'', infinitive form of the verb ``have'', base form of the lexical verb, past tense form of the lexical verb, -ing form of the lexical verb, infinitive of lexical verb, past participle form of the lexical verb and -s form of the lexical verb; conjunctions; articles and interjections. Among the tweets analyzed, more posts utilized formal rather than informal language. More emoticons than punctuation marks were used by Twitter users to express themselves. Moreover, the Twitter users analyzed had more positive than negative sentiments in their tweet posts. Future researchers can expand this study and look into the other grammatical features of Twitter English that may be a basis for instructional materials development.},
year = {2013},
month = {Jan},
date-added = {2013-05-08 18:10:04 +0100},
date-modified = {2013-06-11 09:57:33 +0100},
URL = {http://www.ejournals.ph/index.php?journal=MSEUFRS&page=article&op=viewArticle&path%255B%255D=6258},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2013/Jalbuena/Linguistic%20Features%20of%20English%20in%20Twitter.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p30963},
read = {Yes},
rating = {0}
}

@article{Oosterveer:2011p24319,
author = {Danny Oosterveer}, 
title = {Influencing {\&} measuring word of mouth on Twitter},
abstract = {During the last decade, the way consumers communicate has significantly changed. This change is facilitated by the World Wide Web as a platform whereby information is no longer produced by a small group of institutions. Instead, a rising number of consumers use the Web to express and disseminate their knowledge, experiences, and opinions about products and services. The transition from traditional broadcasting to "Web 2.0" has greatly expanded the opportunities for brands to use bidirectional communication.
Using over 250.000 tweets produced by brands and consumers during a 10 week research period, the effect of strategies as suggested by professional literature on a brand's influence on consumer tweets was investigated. As a social medium, Twitter is one of the 2.0 platforms which gained enormous popularity over the last years.
While a growing amount of people is interacting online, it is essential for brands to understand what strategies might be used to increase their influence over consumer word of mouth. It stresses the need for brands to develop an online presence on social media, thereby increasing the need for knowledge on influence. This study scientifically investigated strategies suggested by professional literature. The current study shows that brands' Twitter strategies positively influence consumer word of mouth. It highlights the importance of one to one communication and community participation. Moreover, it shows that following consumers primarily influences the followers indegree. Although the research has been executed on Twitter alone, its results may be applied universally across social media. The study confirms the effectiveness of conversing with consumers, bringing consumers together around a specific topic or brand, and listening to consumers. As such, its findings may be used to improve strategies for e.g. microblogging, social network sites and other social media.
The current study shows four indicators (follower indegree, mentions criterion, sentiment and retweet criterion) brands can use to measure their influence on consumer word of mouth. The results of this study assist marketers with quantifying influence on Twitter. It builds further on the knowledge of measuring online activities, and will help marketers reporting back to the management. Certain structural aspects of Twitter may seem medium specific. However, a first degree network, content replication, sentiment analysis and brand mentions expressing the conversational exchange all are medium to highly visible for other social media. Hence the results are characterized by a high external validity across social media.
The study puts reach into perspective. Although the first degree network is a highly valid measure of online influence, a strategic focus on direct reach has a minimal effect on the conversational exchange and even negatively impacts the other measures. The findings stress the fundamental relevance of conversational exchange for brands to increase online influence. For online brand management it is crucial to measure online conversations in order to keep track of a brand's online influence. Results of the current study impact online brand management in the sense that they help brands understanding, managing and monitoring consumer word of mouth across the social web. The study confirms the relevance of consumer word of mouth for online branding in this communication 2.0 era.},
pages = {1--60},
year = {2011},
month = {Aug},
date-added = {2011-10-27 08:59:09 +0100},
date-modified = {2012-04-18 14:10:51 +0100},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Oosterveer/Influencing%20&%20measuring%20word%20of.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p24319},
read = {Yes},
rating = {0}
}

@article{Zubiaga:2011p23142,
author = {A Zubiaga and D Spina and V Fresno and R Mart{\'\i}nez}, 
journal = {CIKM' 11},
title = {Classifying Trending Topics: A Typology of Conversation Triggers on Twitter},
abstract = {Twitter summarizes the great deal of messages posted by users in the form of trending topics that reflect the top conversations being discussed at a given moment. These trend- ing topics tend to be connected to current affairs. Different happenings can give rise to the emergence of these trending topics. For instance, a sports event broadcasted on TV, or a viral meme introduced by a community of users. Detecting the type of origin can facilitate information filtering, enhance real-time data processing, and improve user experience. In this paper, we introduce a typology to categorize the triggers that leverage trending topics: news, current events, memes, and commemoratives. We define a set of straightforward language-independent features that rely on the social spread of the trends to discriminate among those types of trending topics. Our method provides an efficient way to immediately and accurately categorize trending topics without need of external data, outperforming a content-based approach.},
year = {2011},
month = {Jan},
date-added = {2011-09-18 11:08:56 +0100},
date-modified = {2012-04-18 14:10:10 +0100},
URL = {http://nlp.uned.es/~damiano/pdf/zubiaga2011trendingtopics.pdf},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Zubiaga/Classifying%20Trending%20Topics%20A%20Typology.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p23142},
rating = {0}
}

@inproceedings{cheong_study_2010,
author = {M Cheong and V Lee}, 
journal = {Proceedings},
title = {A Study on Detecting patterns in Twitter Intra-Topic User and Message Clustering},
abstract = {Timely detection of hidden patterns is the key for the analysis and estimating of driving determinants for mission critical decision making. This study applies Cheong and Lee's ``context-aware'' content analysis framework to extract latent properties from Twitter messages (tweets). In addition, we incorporate an unsupervised Self-organizing Feature Map (SOM) as a machine learning-based clustering tool that has not been investigated in the context of opinion mining and sentimental analysis using microblogging. Our experimental results reveal the detection of interesting patterns for topics of interest which are latent and cannot be easily detected from the observed tweets without the aid of machine learning tools.},
affiliation = {Clayton, Victoria, Australia},
pages = {3125--3128},
year = {2010},
keywords = {decision making, Visualization, opinion mining, machine learning-based clustering tool, Group interaction: analysis of verbal and non-verbal communication, Twitter, sentimental analysis, Communities, social networking (online), pattern detection, Nominations and elections, Media, Twitter messages, microblogging, Online documents, context-aware content analysis framework, self-organizing feature map, pattern clustering, message clustering, twitter intratopic user, Clustering algorithms, Pattern recognition systems and applications}, 
date-added = {2013-04-13 21:02:22 +0100},
date-modified = {2013-06-11 15:40:09 +0100},
doi = {10.1109/ICPR.2010.765},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2010/Cheong/A%20Study%20on%20Detecting%20patterns%20in%20Twitter%20Intra-Topic%20User%20and.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p30601},
rating = {0}
}

@article{Chaudhari:2012p29817,
author = {G Chaudhari}, 
title = {Twitter Data Analysis},
abstract = {Twitter, as a social media, is a very popular micro-blogging service. Through Twitter, people can tell others what they are doing, what they are thinking or what is happening around them. Due to millions of users, Twitter is able to infer something about a given topic as a collective wisdom of different communities all over the world having largely varying opinions. With such huge amount of information that is shared over the Twitter network, a lot of research work is currently being carried out in this field of twitter information extraction to gain some useful insights. This report will discuss some of the recent research in Twitter domain.},
year = {2012},
date-added = {2012-10-26 12:49:47 +0100},
date-modified = {2012-11-03 14:39:40 +0000},
pmid = {related:pi1P7avYkcsJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2012/Chaudhari/Twitter%20Data%20Analysis.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p29817},
rating = {0}
}

@article{Chalmers:2011p24324,
author = {D Chalmers and S Fleming and I Wakeman and D Watson}, 
journal = {informatics.sussex.ac.uk},
title = {Rhythms in Twitter},
abstract = {We have examined a Twitter data set, focusing on temporal patterns observed in users' tweets and in the conversations formed by interacting users -- rather than a network described by follows relations, or aggregate patterns. We have found the bursty behaviour predicted by Barabasi, but with complex patterns to the bursts. By using a clustering algorithm to group intervals between tweets, we have found that conversations show a different pattern of inter-tweet intervals to individuals, tending to: have a higher volume of quick replies; take shorter breaks; and that the timing is more variable.},
year = {2011},
month = {Jan},
date-added = {2011-10-27 23:13:30 +0100},
date-modified = {2013-06-11 15:41:31 +0100},
URL = {http://www.informatics.sussex.ac.uk/users/dc52/Papers/twitter-rhythm.pdf},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Chalmers/Rhythms%20in%20Twitter.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p24324},
read = {Yes},
rating = {0}
}

@article{McKenzie:2011p25574,
author = {D McKenzie and B Ozler}, 
title = {The impact of economics blogs},
abstract = {There is a proliferation of economics blogs, with increasing numbers of economists attracting large numbers of readers, yet little is known about the impact of this new medium. Using a variety of experimental and non-experimental techniques, this study quantifies some of their effects. First, links from blogs cause a striking increase in the number of abstract views and downloads of economics papers. Second, blogging raises the profile of the blogger (and his or her institution) and boosts their reputation above economists with similar publication records. Finally, a blog can transform attitudes about some of the topics it covers.},
year = {2011},
date-added = {2012-01-01 19:53:40 +0000},
date-modified = {2013-06-11 14:08:43 +0100},
pmid = {11920219658376390498related:Yicnjp8gbaUJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/McKenzie/The%20impact%20of%20economics%20blogs.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p25574},
rating = {0}
}

@article{page_linguistics_2012,
author = {Ruth Page}, 
journal = {Discourse \{\&} Communication},
title = {The Linguistics of Self-Branding and Micro-Celebrity in Twitter: The Role of Hashtags},
abstract = {Twitter is a linguistic marketplace (Bourdieu, 1977) in which the processes of self-branding and micro-celebrity (Marwick, 2010) depend on visibility as a means of increasing social and economic gain. Hashtags are a potent resource within this system for promoting the visibility of a Twitter update (and, by implication, the update's author). This study analyses the frequency, types and grammatical context of hashtags which occurred in a dataset of approximately 92,000 tweets, taken from 100 publically available Twitter accounts, comparing the discourse styles of corporations, celebrity practitioners and `ordinary' Twitter members. The results suggest that practices of self-branding and micro-celebrity operate on a continuum which reflects and reinforces the social and economic hierarchies which exist in offline contexts. Despite claims that hashtags are `conversational', this study suggests that participatory culture in Twitter is not evenly distributed, and that the discourse of celebrity practitioners and corporations exhibits the synthetic personalization (Fairclough, 1989) typical of mainstream media forms of broadcast talk.},
note = {Journal Article},
number = {2},
pages = {181--201},
volume = {6},
year = {2012},
date-added = {2013-04-13 21:02:21 +0100},
date-modified = {2013-04-13 21:02:22 +0100},
doi = {10.1177/1750481312437441},
URL = {http://dcm.sagepub.com/cgi/content/abstract/6/2/181},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2012/Page/The%20Linguistics%20of%20Self-Branding%20and%20Micro-Celebrity%20in%20Twitter%20The%20Role.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p30615},
read = {Yes},
rating = {0}
}

@article{ODonovan:2013p29777,
author = {J O'Donovan and B Kang and G Meyer and T H{\"o}llerer and S Adalı}, 
journal = {visual.cs.ucsb.edu
},
title = {Credibility in Context: An Analysis of Feature Distributions in Twitter},
abstract = {Twitter is a major forum for rapid dissemination of user-provided content in real time. As such, a large proportion of the information it contains is not particularly relevant to many users and in fact is perceived as unwanted 'noise' by many. There has been increased research interest in predicting whether tweets are relevant, newsworthy or credible, using a variety of models and methods. In this paper, we focus on an analysis that highlights the utility of the individual features in Twitter such as hashtags, retweets and mentions for predicting credibility. We first describe a context-based evaluation of the utility of a set of features for predicting manually provided credibility assessments on a corpus of microblog tweets. This is followed by an evaluation of the distribution/presence of each feature across 8 diverse crawls of tweet data. Last, an analysis of feature distribution across dyadic pairs of tweets and retweet chains of various lengths is described. Our results show that the best indicators of credibility include URLs, mentions, retweets and tweet length and that features occur more prominently in data describing emergency and unrest situations.},
date-added = {2012-10-18 01:25:15 +0100},
date-modified = {2013-06-11 13:09:14 +0100},
URL = {http://visual.cs.ucsb.edu/documents/papers/Credibility%2520in%2520Context%2520An%2520Analysis%2520of%2520Feature%2520Distributions%2520in%2520Twitter.pdf},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/Unknown/O'Donovan/Credibility%20in%20Context%20An%20Analysis%20of%20Feature%20Distributions%20in%20Twitter.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p29777},
rating = {0}
}

@article{Mocanu:2012p30459,
author = {Delia Mocanu and Andrea Baronchelli and Bruno Gon{\c c}alves and Nicola Perra and Alessandro Vespignani}, 
journal = {arXiv},
title = {The Twitter of Babel: Mapping World Languages through Microblogging Platforms},
abstract = {Large scale analysis and statistics of socio-technical systems that just a few short years ago would have required the use of consistent economic and human resources can nowadays be conveniently performed by mining the enormous amount of digital data produced by human activities. Although a characterization of several aspects of our societies is emerging from the data revolution, a number of questions concerning the reliability and the biases inherent to the big data "proxies" of social life are still open. Here, we survey worldwide linguistic indicators and trends through the analysis of a large-scale dataset of microblogging posts. We show that available data allow for the study of language geography at scales ranging from country-level aggregation to specific city neighborhoods. The high resolution and coverage of the data allows us to investigate different indicators such as the linguistic homogeneity of different countries, the touristic seasonal patterns within countries and the geographical distribution of different languages in multilingual regions. This work highlights the potential of geolocalized studies of open data sources to improve current analysis and develop indicators for major social phenomena in specific communities.},
eprint = {1212.5238v1},
volume = {physics.soc-ph},
year = {2012},
month = {Dec},
keywords = {cs.CL, cs.SI, physics.soc-ph}, 
date-added = {2013-01-25 11:50:35 +0000},
date-modified = {2013-01-25 11:51:00 +0000},
pmid = {1212.5238v1},
URL = {http://arxiv.org/abs/1212.5238v1},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2012/Mocanu/The%20Twitter%20of%20Babel%20Mapping%20World%20Languages%20through%20Microblogging%20Platforms.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p30459},
rating = {0}
}

@article{OConnor:2010p962,
author = {B O'Connor and R Balasubramanyan and B R Routledge and N A Smith}, 
journal = {Proceedings of the Fourth International AAAI Conference on Weblogs and Social Media},
title = {From Tweets to polls: Linking text sentiment to public opinion time series},
abstract = {We connect measures of public opinion measured from polls with sentiment measured from text. We analyze several surveys on consumer confidence and political opinion over the 2008 to 2009 period, and find they correlate to sentiment word frequencies in contempora- neous Twitter messages. While our results vary across datasets, in several cases the correlations are as high as 80%, and capture important large-scale trends. The results highlight the potential of text streams as a substi- tute and supplement for traditional polling.},
year = {2010},
month = {Jan},
keywords = {sa}, 
date-added = {2010-10-31 19:52:49 +0000},
date-modified = {2012-04-18 14:09:18 +0100},
pmid = {4705145563301769490related:EnEb_fUITEEJ},
URL = {http://www.aaai.org/ocs/index.php/ICWSM/ICWSM10/paper/viewPDFInterstitial/1536/1842},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2010/O'Connor/From%20Tweets%20to%20polls%20Linking%20text%20sentiment%20to%20public%20opinion-1.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p962},
read = {Yes},
rating = {5}
}

@article{Tokuhisa:2008p2547,
author = {R Tokuhisa and K Inui and Y Matsumoto}, 
journal = {Proceedings of the 22nd International Conference on Computational Linguistics-Volume 1},
title = {Emotion classification using massive examples extracted from the web},
abstract = {In this paper, we propose a data-oriented method for inferring the emotion of a speaker conversing with a dialog system from the semantic content of an utterance. We first fully automatically obtain a huge collection of emotion-provoking event instances from the Web. With Japanese chosen as a target language, about 1.3 million emotion provoking event instances are extracted using an emotion lexicon and lexical patterns. We then decompose the emo- tion classification task into two sub-steps: sentiment polarity classification (coarse-grained emotion classification), and emo- tion classification (fine-grained emotion classification). For each subtask, the collection of emotion-proviking event instances is used as labelled examples to train a classifier. The results of our experiments indicate that our method signif- icantly outperforms the baseline method. We also find that compared with the single-step model, which applies the emotion classifier directly to inputs, our two-step model significantly reduces sentiment polarity errors, which are considered fatal errors in real dialog applications.},
pages = {881--888},
year = {2008},
date-added = {2010-11-08 14:41:15 +0000},
date-modified = {2012-04-18 14:10:56 +0100},
pmid = {7565450999337823053related:TasntZnh_WgJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2008/Tokuhisa/Emotion%20classification%20using%20massive%20examples%20extracted%20from%20the%20web.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p2547},
read = {Yes},
rating = {0}
}

@article{Davis:2013p31941,
author = {Bud Davis}, 
journal = {Pepperdine Journal of Communication Research},
title = {Hashtag Politics: The Polyphonic Revolution of{\#} Twitter},
number = {1},
pages = {4},
volume = {1},
year = {2013},
date-added = {2013-07-10 10:04:56 +0100},
date-modified = {2013-07-10 10:05:12 +0100},
pmid = {related:xwTQLx2FYPIJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2013/Davis/Hashtag%20Politics%20The%20Polyphonic%20Revolution%20of%23%20Twitter.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p31941},
rating = {0}
}

@article{Lindqvist:2011p24220,
author = {A Lindqvist}, 
journal = {lnu.diva-portal.org},
title = {Trickin', wanna and ain't: Gender differences in the use of vernacular verb forms on Twitter},
abstract = {The Internet site Twitter carries features of spontaneous and unedited informal language which makes it perfect for linguistic studies because people tend to write without trying to correct the language. Men and women use language differently in, for example, online interactions but there also exist similarities between the two sexes. The aim of this study is to investigate these differences and similarities between men's and women's use of vernacular forms on Twitter. In order to achieve the aim, 4000 tweets were collected and analysed from participants of both sexes to establish their different use of vernacular verb forms. The result turned out to be very surprising because previous studies, for example the study by Fischer (1958) within the same area, have shown that men tend to use vernacular forms more than women. Note, that the previous studies are based on offline interactions while this study is based on an online communication. However, this study showed that women used more vernacular verb forms than men on Twitter. This could be the case because women might want to sound more aggressive and masculine for some reason by using the non-standard forms on Twitter. If a different investigation within the same area were carried out, the result might be different because this study is limited to the analysis of only one Internet source.},
year = {2011},
date-added = {2011-10-13 02:55:42 +0100},
date-modified = {2012-04-18 14:09:13 +0100},
URL = {http://lnu.diva-portal.org/smash/get/diva2:431162/FULLTEXT02},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Lindqvist/Trickin'%20wanna%20and%20ain't%20Gender%20differences%20in%20the%20use%20of.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p24220},
read = {Yes},
rating = {0}
}

@article{Mao:2012p28817,
author = {Y Mao and B Wang and W Wei and B Liu}, 
journal = {nlab.engr.uconn.edu
},
title = {Correlating S{\&}P 500 Stocks with Twitter Data},
abstract = {Twitter is a widely used online social media. One important characteristic of Twitter is its real-time nature. In this pa- per, we investigate whether the daily number of tweets that mention Standard {\&} Poor 500 (S{\&}P 500) stocks is corre- lated with S{\&}P 500 stock indicators (stock price and traded volume) at three different levels, from the stock market to industry sector and individual company stocks. We further apply a linear regression with exogenous input model to pre- dict stock market indicators, using Twitter data as exoge- nous input. Our preliminary results demonstrate that daily number of tweets is correlated with certain stock market in- dicators at each level. Furthermore, it appears that Twitter is helpful to predict stock market. Specifically, at the stock market level, we find that whether S{\&}P 500 closing price will go up or down can be predicted more accurately when including Twitter data in the model.},
year = {2012},
month = {Jan},
date-added = {2012-09-30 21:14:42 +0100},
date-modified = {2013-01-01 14:03:47 +0000},
URL = {http://nlab.engr.uconn.edu/papers/stock.pdf},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2012/Mao/Correlating%20S&P%20500%20Stocks%20with%20Twitter%20Data.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p28817},
read = {Yes},
rating = {0}
}

@article{Goncalves:2011p22214,
author = {B Gon{\c c}alves and N Perra and A Vespignani}, 
journal = {PLoS ONE},
title = {Modeling Users' Activity on Twitter Networks: Validation of Dunbar's Number},
abstract = {Microblogging and mobile devices appear to augment human social capabilities, which raises the question whether they remove cognitive or biological constraints on human communication. In this paper we analyze a dataset of Twitter conversations collected across six months involving 1.7 million individuals and test the theoretical cognitive limit on the number of stable social relationships known as Dunbar's number. We find that the data are in agreement with Dunbar's result; users can entertain a maximum of 100--200 stable relationships. Thus, the `economy of attention' is limited in the online world by cognitive and biological constraints as predicted by Dunbar's theory. We propose a simple model for users' behavior that includes finite priority queuing and time resources that reproduces the observed social behavior.},
number = {8},
volume = {6},
year = {2011},
month = {Jan},
date-added = {2011-08-15 07:56:45 +0100},
date-modified = {2012-04-18 14:09:43 +0100},
doi = {10.1371/journal.pone.0022656},
URL = {http://dx.plos.org/10.1371/journal.pone.0022656},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Gon%C3%A7alves/Modeling%20Users'%20Activity%20on%20Twitter%20Networks%20Validation%20of%20Dunbar's%20Number.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p22214},
rating = {0}
}

@article{Lee:2010p3641,
author = {R Lee and K Sumiya}, 
journal = {LBSN '10: Proceedings of the 2nd ACM SIGSPATIAL International Workshop on Location Based Social Networks},
title = {Measuring geographical regularities of crowd behaviors for Twitter-based geo-social event detection},
abstract = {Recently, microblogging sites such as Twitter have garnered a great deal of attention as an advanced form of location-aware social network services, whereby individuals can easily and instantly share their most recent updates from any place. In this study, we aim to develop a geo-social event detection system by monitoring crowd behaviors indirectly via Twitter. In particular, we attempt to find out the occurrence of local events such as local festivals; a considerable number of Twitter users probably write many posts about these events. To detect such unusual geo-social events, we depend on geographical regularities deduced from the usual behavior patterns of crowds with geo-tagged microblogs. By comparing these regularities with the estimated ones, we decide whether there are any unusual events happening in the monitored geographical area. Finally, we describe the experimental results to evaluate the proposed unusuality detection method on the basis of geographical regularities obtained from a large number of geo- tagged tweets around Japan via Twitter.},
year = {2010},
month = {Nov},
keywords = {geographical regularity, geo-social event detection, microblogs}, 
date-added = {2010-11-26 16:53:33 +0000},
date-modified = {2012-04-18 14:09:50 +0100},
URL = {http://portal.acm.org/ft_gateway.cfm?id=1867701&type=pdf&coll=DL&dl=GUIDE&CFID=116090877&CFTOKEN=46873869},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2010/Lee/Measuring%20geographical%20regularities%20of%20crowd%20behaviors%20for%20Twitter-based%20geo-social%20event.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p3641},
read = {Yes},
rating = {0}
}

@article{Herdagdelen:2013p27427,
author = {Ama{\c c} Herda{\u g}delen}, 
journal = {Language Resources and Evaluation},
title = {Twitter n-gram corpus with demographic metadata},
pages = {1--21},
date-added = {2012-02-24 21:50:27 +0000},
date-modified = {2013-07-12 09:22:41 +0100},
pmid = {related:Xj8Wb86Abh0J},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/Unknown/Herda%C4%9Fdelen/Twitter%20n-gram%20corpus%20with%20demographic%20metadata.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p27427},
rating = {0}
}

@article{Krishnamurthy:2008p4789,
author = {B Krishnamurthy and P Gill and Martin Arlitt}, 
journal = {Proceedings of the first workshop on Online social networks},
title = {A few chirps about twitter},
abstract = {Web 2.0 has brought about several new applications that have en- abled arbitrary subsets of users to communicate with each other on a social basis. Such communication increasingly happens not just on Facebook and MySpace but on several smaller network applica- tions such as Twitter and Dodgeball. We present a detailed charac- terization of Twitter, an application that allows users to send short messages. We gathered three datasets (covering nearly 100,000 users) including constrained crawls of the Twitter network using two different methodologies, and a sampled collection from the publicly available timeline. We identify distinct classes of Twitter users and their behaviors, geographic growth patterns and current size of the network, and compare crawl results obtained under rate limiting constraints.},
pages = {19--24},
year = {2008},
date-added = {2010-12-16 17:40:06 +0000},
date-modified = {2013-06-11 14:19:51 +0100},
pmid = {386010660995067638related:9u4fqKZiWwUJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2008/Krishnamurthy/A%20few%20chirps%20about%20twitter.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p4789},
read = {Yes},
rating = {0}
}

@article{Evans:2011p21138,
author = {A Evans and J Twomey and S Talan}, 
journal = {Public Relations Journal},
title = {Twitter as a Public Relations Tool},
abstract = {Using in-depth interviews with executive-level public relations professionals, this study explores the uses of Twitter in communications campaigns. Findings suggest that public relations practitioners consider microblogging to be a valuable asset to a campaign's social media strategy. They believe that Twitter offers a form of communication not offered by other social media applications, and they believe microblogging will continue to be an essential part of an integrated communications campaign.},
number = {1},
volume = {5},
year = {2011},
month = {Jan},
date-added = {2011-07-12 12:53:10 +0100},
date-modified = {2012-04-18 14:10:52 +0100},
URL = {http://www.prsa.org/SearchResults/download/6D-050103/0/Twitter_as_a_Public_Relations_Tool},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Evans/Twitter%20as%20a%20Public%20Relations.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p21138},
rating = {0}
}

@article{RD:2011p16766,
author = {Waters R.D. and J.Y Jamal}, 
journal = {Public Relations Review},
title = {Tweet, tweet, tweet: A content analysis of nonprofit organizations' Twitter updates},
abstract = {Many of the relationship cultivation strategies and the dialogic principles assume sym- metrical communication is taking place. However, significant amounts of information are shared in a one-way manner. Although they have fallen out of favor with many academics, the four models of public relations can provide significant insights into how organizations communicate. Using the models as the guiding framework, this brief study examines how nonprofit organizations from the Philanthropy 200 communicate on Twitter. The findings reveal that the organizations are more likely to use one-way models despite the potential for dialogue and community building on the social networking site.},
year = {2011},
month = {Jan},
date-added = {2011-04-20 21:48:01 +0100},
date-modified = {2012-04-18 14:10:12 +0100},
doi = {10.1016/j.pubrev.2011.03.002},
URL = {http://linkinghub.elsevier.com/retrieve/pii/S0363811111000361},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/R.D./Tweet%20tweet%20tweet%20A%20content%20analysis%20of%20nonprofit%20organizations'%20Twitter.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p16766},
read = {Yes},
rating = {0}
}

@article{Pal:2011p14460,
author = {A Pal and S Counts}, 
journal = {Proceedings of the fourth ACM international {\ldots}},
title = {Identifying topical authorities in microblogs},
abstract = {Content in microblogging systems such as Twitter is produced by tens to hundreds of millions of users. This diversity is a notable strength, but also presents the challenge of finding the most interesting and authoritative authors for any given topic. To address this, we first propose a set of features for characterizing social media authors, including both nodal and topical metrics. We then show how probabilistic clustering over this feature space, followed by a within-cluster ranking procedure, can yield a final list of top authors for a given topic. We present results across several topics, along with results from a user study confirming that our method finds authors who are significantly more interesting and authoritative than those resulting from several baseline conditions. Additionally our algorithm is computationally feasible in near real-time scenarios making it an attractive alternative for capturing the rapidly changing dynamics of microblogs.},
year = {2011},
month = {Jan},
date-added = {2011-03-14 20:50:35 +0000},
date-modified = {2012-04-18 14:10:14 +0100},
doi = {10.1145/1935826.1935843 },
pmid = {16847853146197419384related:eGULNyyZz-kJ},
URL = {http://portal.acm.org/citation.cfm?id=1935843},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Pal/Identifying%20topical%20authorities%20in%20microblogs.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p14460},
rating = {0}
}

@article{Veltri:2012p30020,
author = {G Veltri}, 
journal = {Public Understanding of Science},
title = {Microblogging and nanotweets: Nanotechnology on Twitter},
abstract = {The social web represents a new arena for local, national and global conversations and will play an increasing role in the public understanding of science. This paper presents an analysis of the representations of nanotechnology on Twitter, analysing over 24,000 tweets in terms of web metrics, latent semantic and sentiment analysis. Results indicate that most active users on nanotechnology are distributed according to a power law distribution and that web metric indicators suggest little conversation on the topic. In terms of content, there is a remarkable similarity with previous studies of nanotechnology's representations in other media outlets. Related to content is the sentiment analysis that indicates predominantly positively loaded words in the corpus. Negative sentiments mainly took the form of uncertainty and fear of the unknown rather than open hostility.},
year = {2012},
month = {Jan},
date-added = {2012-12-25 13:48:02 +0000},
date-modified = {2012-12-25 13:51:31 +0000},
URL = {http://pus.sagepub.com/content/early/2012/11/05/0963662512463510.abstract},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2012/Veltri/Microblogging%20and%20nanotweets%20Nanotechnology%20on%20Twitter.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p30020},
rating = {0}
}

@article{Bakshy:2011p24321,
author = {E Bakshy and J Hofman and WA Mason and DJ Watts}, 
journal = {Procceddings of WSDM 2011, Hong Kong},
title = {Identifying 'influencers' on twitter},
abstract = {Word-of-mouth diffusion of information is of great interest to planners, marketers and social network researchers alike. In this work we investigate the attributes and relative influence of 1.6M Twitter users by tracking 39 million diffusion events that took place on the Twitter follower graph over a two month interval in 2009. We find that the largest cascades tend to be generated by users who have been influential in the past and from URLs that were rated more interesting and/or elicited more positive feelings by workers on Mechan- ical Turk. However, individual-level predictions of which user or URL will generate large cascades are relatively unre- liable. We conclude, therefore, that word-of-mouth diffusion can only be harnessed reliably by targeting large numbers of potential influencers, thereby capturing average effects. Fi- nally, we consider a family of hypothetical marketing strate- gies, and find that under a wide range of plausible assump- tions the most cost-effective performance can be realized us- ing ``ordinary influencers''---individuals who exert average or even less-than-average influence.},
year = {2011},
month = {Jan},
date-added = {2011-10-27 09:08:43 +0100},
date-modified = {2012-04-18 14:09:31 +0100},
pmid = {4966183514898465343},
URL = {http://files.embedit.in/embeditin/files/JkYAvlD6p7/1/file.pdf},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Bakshy/Identifying%20'influencers'%20on%20twitter.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p24321},
rating = {0}
}

@article{Gao:2012p27694,
author = {Q Gao and F Abel and GJ Houben and Y Yu}, 
title = {A Comparative Study of Users' Microblogging Behavior on Sina Weibo and Twitter},
abstract = {In this article, we analyze and compare user behavior on two different microblogging platforms: (1) Sina Weibo which is the most popular microblogging service in China and (2) Twitter. Such a com- parison has not been done before at this scale and is therefore essential for understanding user behavior on microblogging services. In our study, we analyze more than 40 million microblogging activities and investigate microblogging behavior from different angles. We (i) analyze how people access microblogs and (ii) compare the writing style of Sina Weibo and Twitter users by analyzing textual features of microposts. Based on se- mantics and sentiments that our user modeling framework extracts from English and Chinese posts, we study and compare (iii) the topics and (iv) sentiment polarities of posts on Sina Weibo and Twitter. Furthermore, (v) we investigate the temporal dynamics of the microblogging behavior such as the drift of user interests over time.
Our results reveal significant differences in the microblogging behavior on Sina Weibo and Twitter and deliver valuable insights for multilingual and culture-aware user modeling based on microblogging data. We also explore the correlation between some of these differences and cultural models from social science research.},
year = {2012},
date-added = {2012-05-05 17:25:24 +0100},
date-modified = {2012-05-05 22:10:35 +0100},
URL = {http://qigao.me/papers/2012-wis-microblog-comp-umap.pdf},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2012/Gao/A%20Comparative%20Study%20of%20Users'%20Microblogging%20Behavior%20on%20Sina%20Weibo.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p27694},
read = {Yes},
rating = {0}
}

@article{Hogenboom:2013p30965,
author = {A Hogenboom and D Bal and F Frasincar and M Bal and F Jong and U Kaymak}, 
journal = {Proceedings of the 28th {\ldots}},
title = {Exploiting emoticons in sentiment analysis},
abstract = {As people increasingly use emoticons in text in order to ex- press, stress, or disambiguate their sentiment, it is crucial for automated sentiment analysis tools to correctly account for such graphical cues for sentiment. We analyze how emoti- cons typically convey sentiment and demonstrate how we can exploit this by using a novel, manually created emoti- con sentiment lexicon in order to improve a state-of-the-art lexicon-based sentiment classification method. We evalu- ate our approach on 2,080 Dutch tweets and forum mes- sages, which all contain emoticons and have been manually annotated for sentiment. On this corpus, paragraph-level accounting for sentiment implied by emoticons significantly improves sentiment classification accuracy. This indicates that whenever emoticons are used, their associated senti- ment dominates the sentiment conveyed by textual cues and forms a good proxy for intended sentiment.},
year = {2013},
month = {Jan},
date-added = {2013-05-08 18:10:04 +0100},
date-modified = {2013-06-10 15:09:23 +0100},
URL = {http://dl.acm.org/citation.cfm?id=2480498},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2013/Hogenboom/Exploiting%20emoticons%20in%20sentiment%20analysis.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p30965},
rating = {0}
}

@article{Papacharissi:2011p23060,
author = {Z Papacharissi and M Oliveira}, 
journal = {tigger.uic.edu},
title = {The Rhythms of News Storytelling on Twitter: Coverage of the January 25th Egyptian uprising on Twitter},
abstract = {Page 1. The Rhythms of News  Storytelling on Twitter : Coverage of the January  25th Egyptian  uprising on Twitter Zizi Papacharissi, PhD Professor and Head, Communication, University of Illinois‐Chicago Maria de Fatima Oliveira ...},
year = {2011},
month = {Jan},
date-added = {2011-09-18 11:07:23 +0100},
date-modified = {2012-04-18 14:10:08 +0100},
URL = {http://tigger.uic.edu/~zizi/Site/Research_files/RhythmsNewsStorytellingTwitterWAPORZPMO.pdf},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Papacharissi/The%20Rhythms%20of%20News%20Storytelling.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p23060},
read = {Yes},
rating = {0}
}

@article{Dodds:2011p31271,
author = {Peter Dodds and Kameron Harris and Isabel Kloumann and Catherine Bliss and Christopher Danforth}, 
journal = {PloS One},
title = {Temporal patterns of happiness and information in a global social network: Hedonometrics and Twitter},
number = {12},
pages = {e26752},
volume = {6},
year = {2011},
date-added = {2013-06-11 15:31:42 +0100},
date-modified = {2013-06-11 15:32:21 +0100},
pmid = {15917654172391560933related:5dbpaiLe5twJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Dodds/Temporal%20patterns%20of%20happiness%20and%20information%20in%20a%20global%20social-1.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p31271},
rating = {0}
}

@misc{bruns_use_2011,
author = {Axel Bruns and Jean E Burgess}, 
journal = {ARC Centre of Excellence for Creative Industries and Innovation; Creative Industries Faculty; Institute for Creative Industries and Innovation},
title = {The Use of Twitter Hashtags in the Formation of Ad-Hoc Publics},
abstract = {As the use of Twitter has become more commonplace throughout many nations, its role in political discussion has also increased. This has been evident in contexts ranging from general political discussion through local, state, and national elections (such as in the 2010 Australian elections) to protests and other activist mobilisation (for example in the current uprisings in Tunisia, Egypt, and Yemen, as well as in the controversy around Wikileaks). Research into the use of Twitter in such political contexts has also developed rapidly, aided by substantial advancements in quantitative and qualitative methodologies for capturing, processing, analysing, and visualising Twitter updates by large groups of users. Recent work has especially highlighted the role of the Twitter hashtag -- a short keyword, prefixed with the hash symbol `\{\#}' -- as a means of coordinating a distributed discussion between more or less large groups of users, who do not need to be connected through existing `follower' networks. Twitter hashtags -- such as `\{\#}ausvotes' for the 2010 Australian elections, `\{\#}londonriots' for the coordination of information and political debates around the recent unrest in London, or `\{\#}wikileaks' for the controversy around Wikileaks thus aid the formation of ad hoc publics around specific themes and topics. They emerge from within the Twitter community -- sometimes as a result of pre-planning or quickly reached consensus, sometimes through protracted debate about what the appropriate hashtag for an event or topic should be (which may also lead to the formation of competing publics using different hashtags). Drawing on innovative methodologies for the study of Twitter content, this paper examines the use of hashtags in political debate in the context of a number of major case studies.},
year = {2011},
keywords = {internet studies, political discussion, 190301 Journalism Studies, Twitter, public communication, 200104 Media Studies, 200100 COMMUNICATION AND MEDIA STUDIES, 200102 Communication Technology and Digital Media Studies, social media, journalism}, 
date-added = {2013-04-13 21:02:22 +0100},
date-modified = {2013-04-13 21:02:22 +0100},
URL = {http://www.ecprnet.eu/conferences/general_conference/reykjavik/},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Bruns/The%20Use%20of%20Twitter%20Hashtags%20in%20the%20Formation%20of%20Ad-Hoc.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p30603},
rating = {0}
}

@article{Koppel:2006p9398,
author = {M Koppel and I Shtrimberg}, 
journal = {Computing Attitude and Affect in Text: Theory and Applications},
title = {Good news or bad news? let the market decide},
abstract = {News stories about publicly traded companies are labeled positive or negative according to price changes of the company stock. It is shown that models based on lexical features can distinguish good news from bad news with accuracy of about 70%. Unfortunately, this works only when stories are labeled according to cotemporaneous price changes but does not work when they are labeled according to subsequent price changes.},
pages = {297--301},
year = {2006},
keywords = {news, method, sa}, 
date-added = {2011-01-25 12:19:32 +0000},
date-modified = {2013-07-08 10:22:23 +0100},
pmid = {5957483839682006573related:LU5g8_w7rVIJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2006/Koppel/Good%20news%20or%20bad%20news?%20let%20the%20market%20decide.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p9398},
read = {Yes},
rating = {5}
}

@article{Williams:2012p29819,
author = {J Williams}, 
journal = {gradworks.umi.com
},
title = {Extracting and modeling typical durations of events and habits from Twitter},
year = {2012},
month = {Jan},
date-added = {2012-10-26 12:49:49 +0100},
date-modified = {2013-06-11 11:49:45 +0100},
URL = {http://gradworks.umi.com/15/14/1514611.html},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2012/Williams/Extracting%20and%20modeling%20typical%20durations%20of%20events%20and%20habits%20from.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p29819},
rating = {0}
}

@article{Sprenger:2010p3019,
author = {T Sprenger and I Welpe}, 
journal = {papers.ssrn.com},
title = {Tweets and Trades-The Information Content of Stock Microblogs},
abstract = {Microblogging forums have become a vibrant online platform to exchange trading ideas and other stock-related information. Using methods from computational linguistics, we analyze roughly 250,000 stock- related microblogging messages, so-called tweets, on a daily basis for the first 6 months of 2010. Our study compares the tweets' sentiment, message volume, and level of agreement with the corresponding market features return, trading volume, volatility, and spread. We find the bullishness of tweets to be associated with abnormal stock returns. However, new information, reflected in the tweets, is incorporated into market prices quickly and market inefficiencies are difficult to exploit with the inclusion of reasonable trading costs. An event study of buy and sell signals shows that microbloggers follow a contrarian strategy. Message volume can predict next-day trading volume. Next to the analysis of tweet and market features, our results offer an explanation for the efficient aggregation of information in microblogging forums. Users who provide above average investment advice are retweeted (i.e., quoted) more often, have more followers and are thus given a greater share of voice in microblogging forums. In sum, we find that stock microblogs contain valuable information that is not yet fully incorporated in current market indicators.},
year = {2010},
date-added = {2010-11-16 18:35:17 +0000},
date-modified = {2013-07-12 11:45:35 +0100},
URL = {http://papers.ssrn.com/sol3/papers.cfm?abstract_id=1702854},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2010/Sprenger/Tweets%20and%20Trades-The%20Information%20Content.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p3019},
read = {Yes},
rating = {5}
}

@article{Go:2010p1773,
author = {A Go and R Bhayani}, 
journal = {stanford.edu},
title = {Exploiting the Unique Characteristics of Tweets for Sentiment Analysis},
abstract = {We present a novel way of utilizing unique characteristics of Twitter data to automatically classify sentiment of Twitter messages. The messages are classified as positive or negative with respect to a query term. This is useful for consumers who want to research the sentiment of products before purchase, or companies that want to monitor the public sentiment of their brands. In this paper we discuss the use of hashtag-related features to improve the performance of a baseline classifier as well as to perform sarcasm detection. We also investigate building separate classifiers for different clusters of Twitter messages. We show a slight improvement in performance using hashtags and a decrease in accuracy for clustering. We also achieve a close-to-human accuracy on sarcasm detection.},
year = {2010},
keywords = {sarcasm, sa, features}, 
date-added = {2010-11-04 10:19:09 +0000},
date-modified = {2012-04-18 14:10:43 +0100},
pmid = {related:6pbjgIaD7xsJ},
URL = {http://www.stanford.edu/~richab86/CS224u.Go.Bhayani.pdf},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2010/Go/Exploiting%20the%20Unique%20Characteristics%20of.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p1773},
read = {Yes},
rating = {5}
}

@article{Guo:2012p29822,
author = {J Guo and P Zhang and L Guo}, 
journal = {Procedia Computer Science},
title = {Mining Hot Topics from Twitter Streams},
abstract = {Mining hot topics from twitter streams has attracted a lot of attention in recent years. Traditional hot topic mining from Internet Web pages were mainly based on text clustering. However, compared to the texts in Web pages, twitter texts are relatively short with sparse attributes. Moreover, twitter data often increase rapidly with fast spreading speed, which poses great challenge to existing topic mining models. To this end, we propose, in this paper, a flexible stream mining approach for hot twitter topic detection. Specifically, we propose to use the Frequent Pattern stream mining algorithm (i.e. FP-stream) to detect hot topics from twitter streams. Empirical studies on real world twitter data demonstrate the utility of the proposed method.},
pages = {2008--2011},
volume = {9},
year = {2012},
date-added = {2012-10-26 12:49:46 +0100},
date-modified = {2012-11-03 14:45:43 +0000},
pmid = {related:kJxOWWJ6PMcJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2012/Guo/Mining%20Hot%20Topics%20from%20Twitter%20Streams.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p29822},
rating = {0}
}

@article{Owoputi:2012p28831,
author = {O Owoputi and B O'Connor and C Dyer and K Gimpel and N Schneider}, 
journal = {ark.cs.cmu.edu
},
title = {Part-of-Speech Tagging for Twitter: Word Clusters and Other Advances},
abstract = {We present improvements to a Twitter part-of-speech tagger, making use of several new features and large- scale word clustering. With these changes, the tagging accuracy increased from 89.2% to 92.8% and the tagging speed is 40 times faster. In addition, we expanded our Twitter tokenizer to support a broader range of Unicode characters, emoticons, and URLs. Finally, we annotate and evaluate on a new tweet dataset, DAILYTWEET547, that is more statistically representative of English-language Twitter as a whole. The new tagger is released as TweetNLP version 0.3, along with the new annotated data and large-scale word clusters at http://www.ark.cs.cmu.edu/TweetNLP.},
year = {2012},
month = {Jan},
date-added = {2012-09-30 22:01:58 +0100},
date-modified = {2012-09-30 22:03:25 +0100},
URL = {http://www.ark.cs.cmu.edu/TweetNLP/owoputi+etal.tr12.pdf},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2012/Owoputi/Part-of-Speech%20Tagging%20for%20Twitter%20Word%20Clusters%20and%20Other%20Advances.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p28831},
read = {Yes},
rating = {0}
}

@article{Pak:2010p4,
author = {A Pak and P Paroubek}, 
journal = {Proceedings of the 5th International Workshop on Semantic Evaluation},
title = {Twitter based system: Using Twitter for disambiguating sentiment ambiguous adjectives},
abstract = {In this paper, we describe our system which participated in the SemEval 2010 task of disambiguating sentiment ambiguous adjectives for Chinese. Our system uses text messages from Twitter, a popu- lar microblogging platform, for building a dataset of emotional texts. Using the built dataset, the system classifies the meaning of adjectives into positive or negative sentiment polarity according to the given context. Our approach is fully automatic. It does not require any additional hand-built language resources and it is language independent.},
pages = {436--439},
year = {2010},
date-added = {2010-10-26 19:52:08 +0100},
date-modified = {2012-04-18 14:10:18 +0100},
pmid = {related:NCxGykRRYgsJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2010/Pak/Twitter%20based%20system%20Using%20Twitter.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p4},
read = {Yes},
rating = {4}
}

@article{Yilmaz:2011p22215,
author = {Y Yilmaz and C Akcora and M Bayir and MF Bulut and M Demirbas}, 
journal = {cse.buffalo.edu},
title = {Trend Sensing via Twitter},
abstract = {Due to its ever increasing popularity, Twitter has become a pervasive information outlet. In this paper, we present a passive sensing framework for identifying trends via Twitter. In our framework, we use a multi-dimensional corpus for finegranularity sensing of trends, and employ both vector-space and set-space methods for achieving accuracy. We present two applications of our framework. The first one is sensing trends in public opinion by using an emotion-category corpus. The second application is sensing trends in location-types in a city by using a location-category corpus. Our experiments show that the proposed methods are able to determine changes in trends effectively in both application scenarios.},
year = {2011},
date-added = {2011-08-15 07:57:32 +0100},
date-modified = {2012-04-18 14:10:59 +0100},
URL = {http://www.cse.buffalo.edu/~mbulut/UBUpdates/wowmom.pdf},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Yilmaz/Trend%20Sensing%20via%20Twitter.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p22215},
rating = {0}
}

@article{Java:2007p3797,
author = {A Java and X Song and T Finin and B Tseng}, 
journal = {Proceedings of the 9th WebKDD and 1st SNA-KDD 2007 workshop on Web mining and social network analysis},
title = {Why we twitter: understanding microblogging usage and communities},
abstract = {Microblogging is a new form of communication in which users can describe their current status in short posts dis- tributed by instant messages, mobile phones, email or the Web. Twitter, a popular microblogging tool has seen a lot of growth since it launched in October, 2006. In this paper, we present our observations of the microblogging phenom- ena by studying the topological and geographical properties of Twitter's social network. We find that people use mi- croblogging to talk about their daily activities and to seek or share information. Finally, we analyze the user intentions associated at a community level and show how users with similar intentions connect with each other.},
pages = {56--65},
year = {2007},
date-added = {2010-12-02 02:43:32 +0000},
date-modified = {2013-06-11 14:35:17 +0100},
pmid = {17863393805918701912related:WImyrAWG5_cJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2007/Java/Why%20we%20twitter%20understanding%20microblogging.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p3797},
read = {Yes},
rating = {0}
}

@article{Pak:2010p2,
author = {A Pak and P Paroubek}, 
journal = {Proceedings of LREC 2010},
title = {Twitter as a corpus for sentiment analysis and opinion mining},
abstract = {Microblogging today has become a very popular communication tool among Internet users. Millions of users share opinions on different aspects of life everyday. Therefore microblogging web-sites are rich sources of data for opinion mining and sentiment analysis. Because microblogging has appeared relatively recently, there are a few research works that were devoted to this topic. In our paper, we focus on using Twitter, the most popular microblogging platform, for the task of sentiment analysis. We show how to automatically collect a corpus for sentiment analysis and opinion mining purposes. We perform linguistic analysis of the collected corpus and explain discovered phenomena. Using the corpus, we build a sentiment classifier, that is able to determine positive, negative and neutral sentiments for a document. Experimental evaluations show that our proposed techniques are efficient and performs better than previously proposed methods. In our research, we worked with English, however, the proposed technique can be used with any other language.},
year = {2010},
keywords = {sa, corpus}, 
date-added = {2010-10-26 19:48:35 +0100},
date-modified = {2013-07-13 13:12:12 +0100},
pmid = {3316879687933033692related:3Pz0qYDsBy4J},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2010/Pak/Twitter%20as%20a%20corpus%20for%20sentiment%20analysis%20and%20opinion%20mining.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p2},
read = {Yes},
rating = {4}
}

@article{Thai:2011p23512,
author = {K Thai and K Zaragoza and T CHristensen}, 
journal = {CHANTS'11},
title = {An implementation for accessing twitter across challenged networks},
abstract = {We describe the challenges, design decisions, and implementation details behind a proof-of-concept application that uses social networking to demonstrate the feasibility behind Delay-Tolerant Networking (DTN) principles. For the main platform, we use DTN2, an implementation of DTN protocols designed for experimentation, production, and deployment. Although this application is specific to Twitter, it is easily modifiable to adapt to other social networks.},
year = {2011},
month = {Jan},
date-added = {2011-09-29 04:02:18 +0100},
date-modified = {2012-04-18 14:09:50 +0100},
URL = {http://dl.acm.org/citation.cfm?id=2030675},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Thai/An%20implementation%20for%20accessing%20twitter%20across%20challenged%20networks.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p23512},
rating = {0}
}

@article{Ritter:2010p14612,
author = {A Ritter and C Cherry and B Dolan}, 
journal = {Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the ACL},
title = {Unsupervised modeling of twitter conversations},
abstract = {We propose the first unsupervised approach to the problem of modeling dialogue acts in an open domain. Trained on a corpus of noisy Twitter conversations, our method discovers dialogue acts by clustering raw utterances. Because it accounts for the sequential behaviour of these acts, the learned model can provide insight into the shape of communication in a new medium. We address the challenge of evaluating the emergent model with a qualitative visualization and an intrinsic conversation ordering task. This work is inspired by a corpus of 1.3 million Twitter conversations, which will be made publicly available. This huge amount of data, available only because Twitter blurs the line between chatting and publishing, highlights the need to be able to adapt quickly to a new medium.},
pages = {172--180},
year = {2010},
month = {Jan},
date-added = {2011-03-24 17:22:00 +0000},
date-modified = {2012-04-18 14:09:45 +0100},
pmid = {11539495314679928038related:5hTIjtmFJKAJ},
URL = {http://portal.acm.org/citation.cfm?id=1858019},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2010/Ritter/Unsupervised%20modeling%20of%20twitter%20conversations.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p14612},
read = {Yes},
rating = {0}
}

@article{Story:2011p18087,
author = {J Story and J Wickstra}, 
journal = {cs.uiowa.edu},
title = {Discovering Trending Topics on Twitter Via Retweets},
abstract = {Over the past few years, Twitter has become the main source on the web for users to share their thoughts through micro-logging. Users can absorb content from those they follow, as well as distribute content to those who follow them. The manner in which this has been streamlined through the Twitter service has allowed Twitter to become a hub for such information passing activities. Whether that information is a user's status update, a link to a news story of particular interest, or a response to a scenario implied by a popular hash tag, trending topics undoubtedly find their way into the vast information network of Twitter.
This project is designed to try and extract those topics which are most popular during a given time frame by examining the nature of the retweets people are posting. We focus on retweets because, intuitively, people tend to pass along the information that most interests themselves, and this will provide a good reflection of what is most important to the Twitter users as a whole We believed that such retweets would provide a glimpse into what topics would be trending or emerging as dominat in Twitter. An analogy would be to consider a retweet as a form of gossip or rumor of an event that spreads before the event becomes known mainstream.
We examine two possible ranking methods for detecting trending and emergent topics based on retweets taking into account a variety of information, such as a user's popularity and characteristics of tweets. Tweets are classified as belonging to one or more pre determined topics generated through use of DMOZ and these topics then ranked using the two aforementioned methods. High ranked topics are then considered trending and compared to the topics Twit- ter considers trending.
After collecting and examining a number of tweets and retweets, it would appear as if retweets make a poor gauge for judging
a topic's popularity. Retweets do not seem to be indicative
of a topic's trending nature or emergent nature. When compared to topics that Twitter considers trending, we saw very little overlap. This may be indicative of the use of a poor scoring system or perhaps that retweets are a poor metric to use to judge a topic's popularity. There may yet still be potential for using retweets to examine topics, but likely requires a better understanding of why users make retweets.
The code used in these tests may be checked out via SVN for
public viewing at http://emerging-topics-retweets.googlecode.com/svn topics-retweets-read-only},
year = {2011},
date-added = {2011-05-13 23:55:07 +0100},
date-modified = {2012-04-18 14:09:59 +0100},
URL = {http://cs.uiowa.edu/~jwickstr/finalPaper.pdf},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Story/Discovering%20Trending%20Topics%20on%20Twitter%20Via%20Retweets.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p18087},
rating = {0}
}

@article{Yang:2007p1295,
author = {Changhua Yang and Kevin Lin and Hsin-Hsi Chen}, 
journal = {WI '07: Proceedings of the IEEE/WIC/ACM International Conference on Web Intelligence},
title = {Emotion Classification Using Web Blog Corpora},
abstract = {In this paper, we investigate the emotion classification of web blog corpora using support vector machine (SVM) and conditional random field (CRF) machine learning techniques. The emotion classifiers are trained at the sentence level and applied to the document level. Our methods also determine an emotion category by taking the context of a sentence into account. Experiments show that CRF classifiers outperform SVM classifiers. When applying emotion classification to a blog at the document level, the emotion of the last sentence in a document plays an important role in determining the overall emotion.},
year = {2007},
month = {Nov},
date-added = {2010-10-31 22:21:55 +0000},
date-modified = {2012-04-18 14:11:00 +0100},
doi = {10.1109/WI.2007.51},
pmid = {1331740.1331857},
URL = {http://portal.acm.org/citation.cfm?id=1331740.1331857},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2007/Yang/Emotion%20Classification%20Using%20Web%20Blog%20Corpora.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p1295},
read = {Yes},
rating = {0}
}

@article{Wagh:2011p24331,
author = {SR Wagh and K Bamane}, 
journal = {Computer Engineering and Intelligent Systems},
title = {Twitter for University using Cloud},
abstract = {In this paper, we present a project that would provide twitter like website for a university purpose intended to use by the students, professors of the colleges in the University and a University Admin. The University admin will provide with all the necessary notifications regarding the events in the University for the students and professors like result notifications, timetables, events, fees, important dates, etc. The students and staff can follow the University Admin and get the necessary notifications just by logging into their accounts and viewing their home pages. Moreover, this project would be deployed on the cloud which would make this website available 24x7 and will reduce the overhead cost of maintaining the expensive servers for the University. This project aims at utilizing the social networking and technology for educational purposes and to improve the student-teacher interaction off the classroom.},
year = {2011},
month = {Jan},
date-added = {2011-10-28 00:24:05 +0100},
date-modified = {2012-04-18 14:10:02 +0100},
URL = {http://www.iiste.org/Journals/index.php/CEIS/article/view/512},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Wagh/Twitter%20for%20University%20using%20Cloud.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p24331},
read = {Yes},
rating = {0}
}

@article{Celli:2011p22957,
author = {F Celli}, 
title = {Mining User Personality in Twitter},
abstract = {The paper describes how we collected and annotated ``Personalitwit'', a corpus of 25700 posts from the popular micro-blogging site Twitter, automatically annotated by user personality and by language with two computational linguistic tools. From the analysis of that data emerged how different writng styles and personality models are associated to different communitites using different devices to post to Twitter.},
year = {2011},
month = {Jan},
date-added = {2011-09-18 11:05:05 +0100},
date-modified = {2013-06-11 15:42:46 +0100},
URL = {http://clic.cimec.unitn.it/fabio/fc11-pr-t.pdf},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Celli/Mining%20User%20Personality%20in%20Twitter.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p22957},
rating = {0}
}

@article{Doan:2012p29778,
author = {S Doan and L Ohno-Machado and N Collier}, 
journal = {arXiv preprint arXiv:1210.0848},
title = {Enhancing Twitter Data Analysis with Simple Semantic Filtering: Example in Tracking Influenza-Like Illnesses},
abstract = {Systems that exploit publicly available user gen- erated content such as Twitter messages have been successful in tracking seasonal influenza. We developed a novel filtering method for Influenza-Like-Ilnesses (ILI)-related messages using 587 million messages from Twitter micro-blogs. We first filtered messages based on syndrome keywords from the BioCaster Ontology, an extant knowledge model of laymen's terms. We then filtered the messages according to semantic features such as negation, hashtags, emoticons, humor and geography. The data covered 36 weeks for the US 2009 influenza season from 30th August 2009 to 8th May 2010. Results showed that our system achieved the highest Pearson correlation coefficient of 98.46% (p-value<2.2e-16), an improvement of 3.98% over the previous state-of-the-art method. The results indicate that simple NLP- based enhancements to existing approaches to mine Twitter data can increase the value of this inexpensive resource.},
year = {2012},
month = {Dec},
date-added = {2012-10-18 01:25:15 +0100},
date-modified = {2012-10-18 01:27:15 +0100},
URL = {http://arxiv.org/abs/1210.0848},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2012/Doan/Enhancing%20Twitter%20Data%20Analysis%20with%20Simple%20Semantic%20Filtering%20Example%20in.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p29778},
read = {Yes},
rating = {0}
}

@inproceedings{huang_conversational_2010,
author = {Jeff Huang and Katherine M Thornton and Efthimis N Efthimiadis}, 
journal = {Proceedings},
title = {Conversational Tagging in Twitter},
abstract = {Users on Twitter, a microblogging service, started the phenome- non of adding tags to their messages sometime around February 2008. These tags are distinct from those in other Web 2.0 systems because users are less likely to index messages for later retrieval. We compare tagging patterns in Twitter with those in Delicious to show that tagging behavior in Twitter is different because of its conversational, rather than organizational nature. We use a mixed method of statistical analysis and an interpretive approach to study the phenomenon. We find that tagging in Twitter is more about filtering and directing content so that it appears in certain streams. The most illustrative example of how tagging in Twitter differs is the phenomenon of the Twitter micro-meme: emergent topics for which a tag is created, used widely for a few days, then disappears. We describe the micro-meme phenomenon and discuss the importance of this new tagging practice for the larger real-time search context.},
affiliation = {Toronto, Ontario, Canada},
pages = {173--178},
year = {2010},
date-added = {2013-04-13 21:02:21 +0100},
date-modified = {2013-06-11 14:40:49 +0100},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2010/Huang/Conversational%20Tagging%20in%20Twitter.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p30606},
rating = {0}
}

@article{Jadhav:2009p1793,
author = {A Jadhav and H Purohit and P Kapanipathi and Pramod Ananthram and A Ranabahu and V Nguyen and P N Mendes and A G Smith and M Cooney and A Sheth}, 
journal = {knoesis.wright.edu},
title = {Twitris 2.0: Semantically Empowered System for Understanding Perceptions From Social Data},
abstract = {We present Twitris 2.0 1, a Semantic Web application that facilitates understanding of social perceptions by Semantics-based pro- cessing of massive amounts of event-centric data. Twitris 2.0 addresses challenges in large scale processing of social data, preserving spatio- temporal-thematic properties. Twitris 2.0 also covers context based se- mantic integration of multiple Web resources and expose semantically enriched social data to the public domain. Semantic Web technologies enable the system's integration and analysis abilities.},
year = {2009},
date-added = {2010-11-04 10:18:02 +0000},
date-modified = {2012-04-18 14:09:13 +0100},
pmid = {related:IZmwaw6OqykJ},
URL = {http://knoesis.wright.edu/library/download/Twitris_ISWC_2010.pdf},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2009/Jadhav/Twitris%202.0%20Semantically%20Empowered%20System.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p1793},
read = {Yes},
rating = {0}
}

@article{Weng:2010p25820,
author = {J Weng and E.P Lim and J Jiang and Q He}, 
journal = {Proceedings of the third ACM international conference on Web search and data mining},
title = {Twitterrank: finding topic-sensitive influential twitterers},
abstract = {This paper focuses on the problem of identifying influential users of micro-blogging services. Twitter, one of the most notable micro-blogging services, employs a social-networking model called ``following'', in which each user can choose who she wants to ``follow'' to receive tweets from without requir- ing the latter to give permission first. In a dataset prepared for this study, it is observed that (1) 72.4% of the users in Twitter follow more than 80% of their followers, and (2) 80.5% of the users have 80% of users they are following follow them back. Our study reveals that the presence of ``reciprocity'' can be explained by phenomenon of homophily [14]. Based on this finding, TwitterRank, an extension of PageRank algorithm, is proposed to measure the influence of users in Twitter. TwitterRank measures the influence taking both the topical similarity between users and the link struc- ture into account. Experimental results show that Twit- terRank outperforms the one Twitter currently uses and other related algorithms, including the original PageRank and Topic-sensitive PageRank.},
pages = {261--270},
year = {2010},
date-added = {2012-01-10 12:15:45 +0000},
date-modified = {2012-04-18 14:10:56 +0100},
pmid = {10089856821779294177related:4ee0MFJfBowJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2010/Weng/Twitterrank%20finding%20topic-sensitive%20influential%20twitterers.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p25820},
rating = {0}
}

@article{Morgan:2013p30515,
author = {J Morgan and C Lampe and M Shafiq}, 
journal = {{\ldots} of the 2013 conference on Computer {\ldots}},
title = {Is news sharing on Twitter ideologically biased?},
abstract = {In this paper we explore effects of perceived ideology of news outlets on consumption and sharing of news in Twitter. Selective exposure theory suggests that when given access to a broad range of information, people will tend to consume and share news that confirms their existing beliefs and biases. We find that users share news in similar ways regardless of outlet or perceived ideology of outlet, and that as a user shares more news content, they tend to quickly include outlets with opposing viewpoints. This suggests that while perceived ideology does not inspire most Twitter users to treat liberal or conservative news outlets differently, it is a factor in their news consumption and sharing. Specifically, users in our sample who sent multiple tweets tended to increase the ideological diversity in news they shared within two or three tweets, and users' information diversity increased as their number of tweets sent increased.},
year = {2013},
month = {Jan},
date-added = {2013-03-05 11:26:05 +0000},
date-modified = {2013-03-05 11:26:29 +0000},
URL = {http://dl.acm.org/citation.cfm?id=2441877},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2013/Morgan/Is%20news%20sharing%20on%20Twitter%20ideologically%20biased?.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p30515},
rating = {0}
}

@article{Kawamoto:2012p29824,
author = {Tatsuro Kawamoto}, 
journal = {Arxiv},
title = {A stochastic model of the tweet diffusion on the Twitter network},
abstract = {We introduce a stochastic model which describes diffusions of tweets on the Twitter network. By dividing the followers into generations, we describe the dynamics of the tweet diffusion as a random multiplicative process. We confirm our model by directly observing the statistics of the multiplicative factors in the Twitter data.},
eprint = {1209.5599v1},
volume = {physics.soc-ph},
year = {2012},
month = {Sep},
keywords = {physics.data-an, physics.soc-ph, cs.SI}, 
date-added = {2012-10-26 12:49:46 +0100},
date-modified = {2012-11-03 15:01:32 +0000},
pmid = {1209.5599v1},
URL = {http://arxiv.org/abs/1209.5599v1},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2012/Kawamoto/A%20stochastic%20model%20of%20the%20tweet%20diffusion%20on%20the%20Twitter.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p29824},
rating = {0}
}

@article{Luo:2013p31148,
author = {Z Luo and M Osborne and J Tang and T Wang}, 
journal = {homepages.inf.ed.ac.uk
},
title = {Who Will Retweet Me? Finding Retweeters in Twitter},
abstract = {ABSTRACT An important aspect of communication in Twitter (and other Social Networks) is message propagation--people creating posts for others to share. Although there has been work on modelling how tweets in Twitter are propagated (retweeted), an untackled ... 
},
year = {2013},
month = {Jan},
date-added = {2013-06-04 17:37:16 +0100},
date-modified = {2013-06-04 17:37:52 +0100},
URL = {http://homepages.inf.ed.ac.uk/miles/papers/sigir13a.pdf},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2013/Luo/Who%20Will%20Retweet%20Me?%20Finding%20Retweeters%20in%20Twitter.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p31148},
rating = {0}
}

@article{Choy:2012p30017,
author = {M Choy}, 
journal = {arXiv preprint arXiv:1211.0938},
title = {US Presidential Election 2012 Prediction using Census Corrected Twitter Model},
abstract = {US Presidential Election 2012 has been a very tight race between the two key candidates. There were intense battle between the two key candidates. The election reflects the sentiment of the electorate towards the achievements of the incumbent President Obama. The campaign lasted several months and the effects can be felt in the internet and twitter. The presidential debates injected new vigor in the challenger's campaign and successfully captured the electorate of several states posing a threat to the incumbent's position. Much of the sentiment in the election has been captured in the online discussions. In this paper, we will be using the original model described in Choy et. al. (2011) using twitter data to forecast the next US president.},
year = {2012},
month = {Jan},
date-added = {2012-12-25 13:48:02 +0000},
date-modified = {2012-12-25 13:48:51 +0000},
URL = {http://arxiv.org/abs/1211.0938},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2012/Choy/US%20Presidential%20Election%202012%20Prediction%20using%20Census%20Corrected%20Twitter%20Model.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p30017},
rating = {0}
}

@article{Bordia:2004p22179,
author = {P Bordia and N Difonzo}, 
journal = {Social Psychology Quarterly},
title = {Problem solving in social interactions on the Internet: Rumor as social cognition},
abstract = {Rumor discourse has been conceptualized as an attempt to reduce anxiety and uncer- tainty via a process of social sensemaking. Fourteen rumors transmitted on various Internet discussion groups were observed and content analyzed over the life of each rumor. With this (previously unavailable) more ecologically robust methodology, the intertwined threads of sensemaking and the gaining of interpretive control are clearly evident in the tapestry of rumor discourse. We propose a categorization of statements (the Rumor Interaction Analysis System) and find differences between dread rumors and wish rumors in anxiety-related content categories. Cluster analysis of these state- ments reveals a typology of voices (``communicative postures'') exhibiting sensemaking activities of the rumor discussion group, such as hypothesizing, skeptical critique, directing of activities to gain information, and presentation of evidence. These findings enrich our understanding of the long-implicated sensemaking function of rumor by clarifying the elements of communication that operate in rumor's social context.},
year = {2004},
month = {Jan},
date-added = {2011-08-11 23:07:02 +0100},
date-modified = {2012-04-18 14:09:55 +0100},
doi = {10.1177/019027250406700105},
pmid = {1550246453307338259related:E26xi--UgxUJ},
URL = {http://spq.sagepub.com/content/67/1/33.short},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2004/Bordia/Problem%20solving%20in%20social%20interactions%20on%20the%20Internet%20Rumor%20as.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p22179},
rating = {0}
}

@article{Kcman:2010p1800,
author = {E Kıcıman}, 
journal = {Web N-gram Workshop},
title = {Language Differences and Metadata Features on Twitter},
abstract = {In the past several years, microblogging services like Twitter and Facebook have become a popular method of communication, allowing users to disseminate and gather information to and from hundreds or thousands (or even millions) of people, often in real-time. As much of the content on microblogging services is publicly accessible, we have recently seen many secondary services being built atop them, including services that perform significant content analysis, such as real-time search engines and trend analysis services. With the eventual goal of building more accurate and less expensive models of microblog streams, this paper investigates the degree to which language variance is related to the metadata of microblog content. We hypothesize that if a strong relationship exists between metadata features and language then we will be able to use this metadata as a trivial classifier to match individual messages with specialized, more accurate language models. To investigate the validity of this hypothesis, we analyze a corpus of over 72M Twitter messages, building language models conditioned on a variety of available message metadata.},
year = {2010},
month = {Jan},
date-added = {2010-11-04 10:13:51 +0000},
date-modified = {2013-06-11 14:21:02 +0100},
pmid = {related:nn6fjcMBG7YJ},
URL = {http://research.microsoft.com/en-us/events/webngram/sigir2010web_ngram_workshop_proceedings.pdf%23page=55},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2010/K%C4%B1c%C4%B1man/Language%20Differences%20and%20Metadata%20Features%20on%20Twitter.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p1800},
read = {Yes},
rating = {0}
}

@article{bruns_quantitative_2012,
author = {Axel Bruns and Stefan Stieglitz}, 
journal = {Journal of Technology in Human Services},
title = {Quantitative Approaches to Comparing Communication Patterns on Twitter},
abstract = {To date, the available literature mainly discusses Twitter activity patterns in the context of individual case studies, while comparative research on a large number of communicative events and their dynamics and patterns is missing. By conducting a comparative study of more than 40 different cases (covering topics such as elections, natural disasters, corporate crises, and televised events) we identify a number of distinct types of discussion that can be observed on Twitter. Drawing on a range of communicative metrics, we show that thematic and contextual factors influence the usage of different communicative tools available to Twitter users, such as original tweets, @replies, retweets, and URLs. Based on this first analysis of the overall metrics of Twitter discussions, we also demonstrate stable patterns in the use of Twitter in the context of major topics and events.},
number = {3-4},
pages = {160--185},
volume = {30},
year = {2012},
date-added = {2013-04-13 21:02:22 +0100},
date-modified = {2013-04-13 21:02:22 +0100},
doi = {10.1080/15228835.2012.744249},
URL = {http://dx.doi.org/10.1080/15228835.2012.744249},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2012/Bruns/Quantitative%20Approaches%20to%20Comparing%20Communication%20Patterns%20on%20Twitter.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p30602},
rating = {0}
}

@article{Go:2009p1068,
author = {A Go and R Bhayani and L Huang}, 
title = {Twitter sentiment classification using distant supervision},
abstract = {We introduce a novel approach for automatically classify- ing the sentiment of Twitter messages. These messages are classified as either positive or negative with respect to a query term. This is useful for consumers who want to re- search the sentiment of products before purchase, or com- panies that want to monitor the public sentiment of their brands. There is no previous research on classifying sen- timent of messages on microblogging services like Twitter. We present the results of machine learning algorithms for classifying the sentiment of Twitter messages using distant supervision. Our training data consists of Twitter messages with emoticons, which are used as noisy labels. This type of training data is abundantly available and can be obtained through automated means. We show that machine learn- ing algorithms (Naive Bayes, Maximum Entropy, and SVM) have accuracy above 80% when trained with emoticon data. This paper also describes the preprocessing steps needed in order to achieve high accuracy. The main contribution of this paper is the idea of using tweets with emoticons for distant supervised learning.},
year = {2009},
month = {Jan},
keywords = {lr, sa}, 
date-added = {2010-10-31 19:56:25 +0000},
date-modified = {2013-07-10 09:37:11 +0100},
pmid = {2244848154150854334related:vl7aooBNJx8J},
URL = {http://www.stanford.edu/~alecmgo/papers/TwitterDistantSupervision09.pdf},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2009/Go/Twitter%20sentiment%20classification%20using%20distant%20supervision.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p1068},
read = {Yes},
rating = {0}
}

@article{Zhang:2010p1795,
author = {W B Zhang and Steven Skiena}, 
journal = {aaai.org},
title = {Trading Strategies To Exploit Blog and News Sentiment},
abstract = {We use quantitative media (blogs, and news as a comparison) data generated by a large-scale natural language processing (NLP) text analysis system to perform a comprehensive and comparative study on how company related news variables anticipates or reflects the company's stock trading volumes and financial returns. Building on our findings, we give a sentiment-based market-neutral trading strategy which gives consistently favorable returns with low volatility over a long period. Our results are significant in confirming the performance of general blog and news sentiment analysis methods over broad domains and sources. Moreover, several remarkable differences between news and blogs are also identified.},
year = {2010},
month = {Jan},
date-added = {2010-11-04 10:12:10 +0000},
date-modified = {2013-07-10 11:43:10 +0100},
pmid = {related:2hbPLjifGC0J},
URL = {http://www.aaai.org/ocs/index.php/ICWSM/ICWSM10/paper/download/1529/1904},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2010/Zhang/Trading%20Strategies%20To%20Exploit%20Blog%20and%20News%20Sentiment.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p1795},
read = {Yes},
rating = {0}
}

@article{Goode:2013p30962,
author = {A Goode}, 
journal = {digital.library.txstate.edu
},
title = {Twitter and Fashion: A Quantitative Investigation of the Use of Twitter as an Interactive Tool by Luxury Fashion Brands},
abstract = {The current study investigated the use of Twitter by luxury fashion brands to interact and engage with consumers. Fashion is a fast-paced, highly visual industry where social media are rapidly growing in popularity. Although there is existing research on marketing and ... 
},
year = {2013},
month = {Jan},
date-added = {2013-05-08 18:10:04 +0100},
date-modified = {2013-05-08 18:13:23 +0100},
URL = {https://digital.library.txstate.edu/handle/10877/4541},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2013/Goode/Twitter%20and%20Fashion%20A%20Quantitative%20Investigation%20of%20the%20Use%20of.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p30962},
rating = {0}
}

@article{Jaffe:2006p2283,
author = {A Jaffe and M Naaman and T Tassa and M Davis}, 
journal = {Proceedings of the 8th ACM international workshop on Multimedia information retrieval},
title = {Generating summaries and visualization for large collections of geo-referenced photographs},
abstract = {We describe a framework for automatically selecting a sum- mary set of photos from a large collection of geo-referenced photographs. Such large collections are inherently difficult to browse, and become excessively so as they grow in size, making summaries an important tool in rendering these col- lections accessible. Our summary algorithm is based on spa- tial patterns in photo sets, as well as textual-topical patterns and user (photographer) identity cues. The algorithm can be expanded to support social, temporal, and other factors. The summary can thus be biased by the content of the query, the user making the query, and the context in which the query is made.
A modified version of our summarization algorithm serves as a basis for a new map-based visualization of large collec- tions of geo-referenced photos, called Tag Maps. Tag Maps visualize the data by placing highly representative textual tags on relevant map locations in the viewed region, effec- tively providing a sense of the important concepts embodied in the collection.
An initial evaluation of our implementation on a set of geo-referenced photos shows that our algorithm and visual- ization perform well, producing summaries and views that are highly rated by users.},
pages = {89--98},
year = {2006},
date-added = {2010-11-08 13:57:27 +0000},
date-modified = {2013-06-11 14:38:38 +0100},
pmid = {16339140615047990985related:yc4XJ9JJwOIJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2006/Jaffe/Generating%20summaries%20and%20visualization%20for%20large%20collections%20of%20geo-referenced%20photographs.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p2283},
read = {Yes},
rating = {5}
}

@article{Bruns:2012p28827,
author = {A Bruns and T Highfield and RA Lind}, 
journal = {Producing Theory: The Intersection of Audiences and Production in a Digital World},
title = {Blogs, Twitter, and breaking news: the produsage of citizen journalism},
abstract = {Debates over the role and relevance of what has been described as citizen journalism have existed at least since the late 1990s; positions have ranged from the fulsome dismissal of such bottom-up journalism activities (and indeed, almost all user-led content creation) as being part of a new "cult ofthe amateur" (Keen, 2007) to nearly equally simplistic perspectives which predicted citizen journalists would replace the mainstream journalism industry within a short timeframe. A more considered, more realistic perspective would take a somewhat more moderate view. Aided by circumstances including the long-term financial crisis enveloping journalism industries in many developed nations, the creeping corporatization and politicization of journalistic activities in democratic and non-democratic countries alike, and the largely unmet challenge of new, Internet-based media fonns, citizen journalism (as well as other parajournalistic media, including TV comedy such as The Daily Show) has been able to make credible inroads into what used to be the domain of journalism proper.},
year = {2012},
date-added = {2012-09-30 21:33:20 +0100},
date-modified = {2013-06-11 15:51:08 +0100},
pmid = {2147691921852504980related:lJv-iGwizh0J},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2012/Bruns/Blogs%20Twitter%20and%20breaking%20news%20the%20produsage%20of%20citizen%20journalism.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p28827},
rating = {0}
}

@article{Stewart:2012p30420,
author = {J Stewart and H Strong and J Parker and M Bedau}, 
journal = {Data Mining Workshops ( {\ldots}},
title = {Twitter Keyword Volume, Current Spending, and Weekday Spending Norms Predict Consumer Spending},
abstract = {We examine whether aggregate daily Twitter key- word volumes over eight months from November 2011 to June 2012 can be used to predict aggregate daily consumer spending as reported by Gallup. We also examine whether Twitter keyword volume improves predictive ability over prediction based solely on current spending, weekday spending norms, and spending history. We divide spending and Twitter data into (i) in-sample data used to identify which Twitter words are highly correlated with spending and to estimate model coefficients, and (ii) out-of- sample data used to measure model forecast success. Our methods are very general and include n-grams (e.g., pairs of words, like ``going shopping''). We note that the historical spending data exhibit a weekday pattern of high spending on two days and low spending over the rest of the week. Spending history also shows some striking deviations from weekday norms, such as Black Friday (the day after the American Thanksgiving holiday) and Boxing day (the day after Christmas)---historically large shopping days. We build models on combinations of Twitter keyword volume (T), current spending (S), and weekday spending norms (D), and compare four model forecast success measures: the correlation between actual and forecast daily spending changes, the percentage of correctly forecast directions of daily spending change, the correlation between actual and forecast deviations from weekday spending norms, and the percentage of correctly forecast deviations from weekday norms. We test model forecasts over the period: April - June. Our results show that weekday Twitter keyword volume, current spending, and weekday spending norms all have significant value for predicting consumer spending three days in advance, but none demonstrates a significant predictive advantage over the others.},
year = {2012},
month = {Jan},
date-added = {2013-01-17 22:30:01 +0000},
date-modified = {2013-01-17 22:31:23 +0000},
URL = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6406514},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2012/Stewart/Twitter%20Keyword%20Volume%20Current%20Spending%20and%20Weekday%20Spending%20Norms%20Predict.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p30420},
rating = {0}
}

@article{Liere:2010p20710,
author = {D Liere}, 
journal = {Proceedings of the International Workshop on MSM'10},
title = {How far does a tweet travel?: Information brokers in the twitterverse},
abstract = {In this paper, I present evidence on the geographic diffusion patterns of information of Twitter users. I identify three possible information diffusion patterns: random, local and information brokerage and show that the information brokerage pattern describes best how users of Twitter diffuse information through the act of retweeting.},
year = {2010},
month = {Jan},
date-added = {2011-06-28 12:41:17 +0100},
date-modified = {2013-06-11 14:12:57 +0100},
pmid = {6743888536069559240related:yFNBleQal10J},
URL = {http://portal.acm.org/citation.cfm?id=1835986},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2010/Liere/How%20far%20does%20a%20tweet.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p20710},
read = {Yes},
rating = {0}
}

@article{Terpstra:2012p29818,
author = {T Terpstra and R Stronkman and A de Vries and GL Paradies}, 
title = {Towards a realtime Twitter analysis during crises for operational crisis management},
year = {2012},
date-added = {2012-10-26 12:49:49 +0100},
date-modified = {2012-11-03 06:09:28 +0000},
pmid = {18145505725609003054related:Lsi9hFHJ0fsJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2012/Terpstra/Towards%20a%20realtime%20Twitter%20analysis%20during%20crises%20for%20operational%20crisis.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p29818},
rating = {0}
}

@article{DeDomenico:2013p30831,
author = {Manlio De Domenico and Antonio Lima and Paul Mougel and Mirco Musolesi}, 
journal = {arXiv preprint arXiv:1301.2952},
title = {The Anatomy of a Scientific Gossip},
year = {2013},
date-added = {2013-04-25 14:57:22 +0100},
date-modified = {2013-04-25 15:01:11 +0100},
pmid = {related:_qYbo3NpKHMJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2013/De%20Domenico/The%20Anatomy%20of%20a%20Scientific%20Gossip.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p30831},
rating = {0}
}

@article{Gangadharbatla:2011p21136,
author = {H Gangadharbatla and M Valafar}, 
journal = {amic.org.sg},
title = {Tweet This: A Preliminary Look At How Information Travels On Twitter},
abstract = {The current study is an exploratory look at how information travels on Twitter. Data was collected in two waves using crawlers for over 30 days from a sample of 300,000 users on a micro-blogging website called Twitter. Findings suggest that (1) a small number of users account for a majority of contribution on Twitter, (2) opinion leaders on Twitter follow other opinion leaders forming a community of influencers, and (3) information dissemination on Twitter follows a power-law distribution. Theoretical and practical implications are drawn for communication professionals.},
year = {2011},
date-added = {2011-07-12 12:46:01 +0100},
date-modified = {2012-04-18 14:10:11 +0100},
URL = {http://amic.org.sg/conference/conf2011/CD/Harsha%2520Gangadharbatla1.doc},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Gangadharbatla/Tweet%20This%20A%20Preliminary%20Look.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p21136},
rating = {0}
}

@article{Byun:2012p30061,
author = {C Byun and H Lee and Y Kim}, 
journal = {Proceedings of the 2012 ACM Research in {\ldots}},
title = {Automated Twitter data collecting tool for data mining in social network},
abstract = {Applying data mining techniques to social media can yield interesting perspectives about individual human behavior, detecting hot issues and topics, or discovering a group and community. However, it is difficult to build your own data set to apply data mining techniques without an automated data gathering system. To overcome this challenge, we developed a java-based data gathering tool that continually collects social data from Twitter. This allows us, as well as other researchers, to build our own Twitter database. In this paper, we introduce the design specifications and explain the implementation details of the Twitter Data Collecting Tool we developed. In addition, we provide an in-depth analysis of Twitter messages about various Super Bowl ads by applying data-mining techniques to a case study. The study aims to address the question of how people use Twitter and to assess the power of Twitter in terms of creating consumer interest in brands and commercials.},
year = {2012},
month = {Jan},
date-added = {2013-01-05 13:02:02 +0000},
date-modified = {2013-06-11 15:48:43 +0100},
URL = {http://dl.acm.org/citation.cfm?id=2401603.2401621},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2012/Byun/Automated%20Twitter%20data%20collecting%20tool%20for%20data%20mining%20in%20social.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p30061},
rating = {0}
}

@article{Xie:2012p28819,
author = {W Xie and C Li and F Zhu and EP Lim and X Gong}, 
journal = {mysmu.edu
},
title = {When a Friend in Twitter is a Friend in Life},
abstract = {Twitter is a fast-growing online social network service (SNS) where users can ``follow'' any other user to re- ceive his or her mini-blogs which are called ``tweets''. In this paper, we study the problem of identifying a user's off-line real-life social community, which we call the user's Twitter off-line community, purely from ex- amining Twitter network structure. Based on obser- vations from our user-verified Twitter data and results from previous works, we propose three principles about Twitter off-line communities. Incorporating these prin- ciples, we develop a novel algorithm to iteratively dis- cover the Twitter off-line community based on a new way of measuring user closeness. According to ground truth provided by real Twitter users, our results demon- strate the effectiveness of our approach with both high precision and recall in most cases.},
year = {2012},
month = {Jan},
date-added = {2012-09-30 21:14:42 +0100},
date-modified = {2013-06-11 11:22:32 +0100},
URL = {http://www.mysmu.edu/faculty/fdzhu/paper/WEBSCI'12.pdf},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2012/Xie/When%20a%20Friend%20in%20Twitter%20is%20a%20Friend%20in%20Life.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p28819},
rating = {0}
}

@article{Cha:2010p1915,
author = {M Cha and H Haddadi and F Benevenuto and K Gummadi}, 
journal = {Proceedings of the Fourth International AAAI Conference on Weblogs and Social Media},
title = {Measuring user influence in twitter: The million follower fallacy},
abstract = {Directed links in social media could represent anything from intimate friendships to common interests, or even a passion for breaking news or celebrity gossip. Such directed links determine the flow of information and hence indicate a user's influence on others---a concept that is crucial in sociology and viral marketing. In this paper, using a large amount of data collected from Twit- ter, we present an in-depth comparison of three mea- sures of influence: indegree, retweets, and mentions. Based on these measures, we investigate the dynam- ics of user influence across topics and time. We make several interesting observations. First, popular users who have high indegree are not necessarily influential in terms of spawning retweets or mentions. Second, most influential users can hold significant influence over a variety of topics. Third, influence is not gained spon- taneously or accidentally, but through concerted effort such as limiting tweets to a single topic. We believe that these findings provide new insights for viral marketing and suggest that topological measures such as indegree alone reveals very little about the influence of a user.},
year = {2010},
month = {Jan},
keywords = {dataset, relationship}, 
date-added = {2010-11-05 05:38:22 +0000},
date-modified = {2012-04-18 14:10:16 +0100},
pmid = {9566759446015269730related:Yltafwf1w4QJ},
URL = {http://www.aaai.org/ocs/index.php/ICWSM/ICWSM10/paper/download/1538/1826},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2010/Cha/Measuring%20user%20influence%20in%20twitter%20The%20million%20follower%20fallacy.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p1915},
read = {Yes},
rating = {4}
}

@article{Esteban:2012p27693,
author = {J Esteban and A Ortega and S McPherson and M Sathiamoorthy}, 
journal = {Arxiv},
title = {Analysis of Twitter Traffic based on Renewal Densities},
abstract = {In this paper we propose a novel approach for Twitter traffic anal- ysis based on renewal theory. Even though twitter datasets are of increasing interest to researchers, extracting information from mes- sage timing remains somewhat unexplored. Our approach, extending our prior work on anomaly detection, makes it possible to character- ize levels of correlation within a message stream, thus assessing how much interaction there is between those posting messages. More- over, our method enables us to detect the presence of periodic traffic, which is useful to determine whether there is spam in the message stream. Because our proposed techniques only make use of timing information and are amenable to downsampling, they can be used as low complexity tools for data analysis.},
year = {2012},
month = {Jan},
date-added = {2012-05-05 17:25:24 +0100},
date-modified = {2012-05-05 22:11:58 +0100},
URL = {http://arxiv.org/abs/1204.3921},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2012/Esteban/Analysis%20of%20Twitter%20Traffic%20based%20on%20Renewal%20Densities.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p27693},
rating = {0}
}

@article{Anger:2011p22995,
author = {I Anger and C Kittl}, 
journal = {Proceedings of the 11th International Conference on Knowledge Management and Knowledge Technologies},
title = {Measuring influence on Twitter},
abstract = {There are currently over 175 million Twitter accounts worldwide, making Twitter one of the most popular and most observed Social Media platform. But Twitter is not so much a social network where the exchange of personal information is facilitated -- in fact, recent surveys state that it's not very social at all with a large amount of inactive accounts and a low motivation of engaging in dialogues [1]. Twitter has rather evolved into a pool of constantly updating information streams consisting of links, short status updates, and eyewitness news. Among the millions of users, a small percentage is what is called the group of influencers or alpha users. They have a large, active audience that consumes and multiplies the content published by the influencer. Thus, an influencer's content -- whether it is plain text or links -- is distributed in a number of micro-networks and receives attention from a large amount of users even though they might not even be direct followers of the influencer. The further the content is spread, the further the influence of the user reaches.
There are various tools that enable performance measurement on Social Media. Some only sum up numbers such as the amount of followers or mentions gained on Twitter; others interpret the numbers and rate the performance using a specific algorithm. An example for the latter is Klout, a popular service that will be looked at more closely, focusing on the question of how Klout calculates its scores which serve as a means of measuring success of Twitter usage.
The research purpose of this paper is to determine a grounded approach for measuring social networking potential of individual Twitter users.},
year = {2011},
month = {Jan},
date-added = {2011-09-18 11:05:38 +0100},
date-modified = {2012-04-18 14:10:13 +0100},
doi = {10.1145/2024288.2024326},
URL = {http://dl.acm.org/citation.cfm?id=2024326},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Anger/Measuring%20influence%20on%20Twitter.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p22995},
rating = {0}
}

@article{Kaufmann:2010p1734,
author = {M Kaufmann}, 
title = {Syntactic Normalization of Twitter Messages},
abstract = {The use of computer mediated communication such as emailing, microblogs, Short Messaging System (SMS), and chat rooms has created corpora which contain incredibly noisy text. Tweets, messages sent by users on Twitter.com, are an especially noisy form of communication. Twitter.com contains billions of these tweets, but in their current state they contain so much noise that it is difficult to extract useful information. Tweets often contain highly irregular syntax and nonstandard use of English. This paper describes a novel system which normalizes these Twitter posts, converting them into a more standard form of English, so that standard machine translation (MT) and natural language processing (NLP) techniques can be more easily applied to them. In order to normalize Twitter tweets, we take a two step approach. We first preprocess tweets to remove as much noise as possible and then feed them into a machine translation model to convert them into standard English. Together, these two steps allow us to achieve improvement in BLEU scores comporable to the improvements achieved by SMS normalization},
year = {2010},
month = {Jan},
date-added = {2010-11-04 10:00:38 +0000},
date-modified = {2012-04-18 14:10:07 +0100},
pmid = {related:bZXYMsT9nz0J},
URL = {http://www.cs.uccs.edu/~kalita/work/reu/REUFinalPapers2010/Kaufmann.pdf},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2010/Kaufmann/Syntactic%20Normalization%20of%20Twitter%20Messages.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p1734},
read = {Yes},
rating = {0}
}

@article{Schumaker:2009p2746,
author = {RP Schumaker and HC Chen}, 
journal = {ACM Transactions on Information},
title = {Textual analysis of stock market prediction using breaking financial news: The AZFin text system},
abstract = {Our research examines a predictive machine learning approach for financial news articles analysis using several different textual representations: bag of words, noun phrases, and named entities. Through this approach, we investigated 9,211 financial news articles and 10,259,042 stock quotes covering the S{\&}P 500 stocks during a five week period. We applied our analysis to estimate a discrete stock price twenty minutes after a news article was released. Using a support vector machine (SVM) derivative specially tailored for discrete numeric prediction and models containing different stock-specific variables, we show that the model containing both article terms and stock price at the time of article release had the best performance in closeness to the actual future stock price (MSE 0.04261), the same direction of price movement as the future price (57.1% directional accuracy) and the highest return using a simulated trading engine (2.06% return). We further investigated the different textual representations and found that a Proper Noun scheme performs better than the de facto standard of Bag of Words in all three metrics.},
number = {2},
pages = {1--19},
volume = {27},
year = {2009},
date-added = {2010-11-09 12:28:47 +0000},
date-modified = {2012-04-18 14:09:27 +0100},
doi = {10.1145/1462198.1462204},
pmid = {5241210560096342539related:C5KROzyFvEgJ},
URL = {http://doi.acm.org/10.1145/1462198.1462204},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2009/Schumaker/Textual%20analysis%20of%20stock%20market%20prediction%20using%20breaking%20financial%20news.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p2746},
read = {Yes},
rating = {0}
}

@article{Abrol:2010p1899,
author = {S Abrol and L Khan}, 
journal = {Proceedings of the 6th Workshop on GIR'10},
title = {TWinner: understanding news queries with geo-content using Twitter},
abstract = {In the present world scenario, where the search engines wars are becoming fiercer than ever, it becomes necessary for each search engine to realize the intent of the user query to be able to provide him with more relevant search results. Amongst the various categories of search queries, a major portion is constituted by those having news intent. Seeing the tremendous growth of social media users, the spatial-temporal nature of the media can prove to be a very useful tool to improve the search quality. In our work we examine the development of such a tool that combines social media in improving the quality of web search and predicting whether the user is looking for news or not. We go one step beyond the previous research by mining Twitter messages, assigning weights to them and determining keywords that can be added to the search query to act as pointers to the existing search engine algorithms suggesting to it that the user is looking for news. We conduct a series of experiments and show the impact that TWinner has on the results.},
year = {2010},
month = {Jan},
keywords = {keyword extracting, geolization}, 
date-added = {2010-11-05 05:40:03 +0000},
date-modified = {2012-04-18 14:10:03 +0100},
pmid = {10996647748022644445related:3S79NN3wm5gJ},
URL = {http://portal.acm.org/citation.cfm?id=1722093&dl=GUIDE,},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2010/Abrol/TWinner%20understanding%20news%20queries%20with%20geo-content%20using%20Twitter-1.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p1899},
read = {Yes},
rating = {4}
}

@article{Marwick:2011p306,
author = {AE Marwick and D Boyd}, 
journal = {New Media {\&} Society},
title = {I tweet honestly, I tweet passionately: Twitter users, context collapse, and the imagined audience},
abstract = {Social media technologies collapse multiple audiences into single contexts, making it difficult for people to use the same techniques online that they do to handle multiplicity in face-to-face conversation.This article investigates how content producers navigate `imagined audiences' on Twitter. We talked with participants who have different types of followings to understand their techniques, including targeting different audiences, concealing subjects, and maintaining authenticity. Some techniques of audience management resemble the practices of `micro-celebrity' and personal branding, both strategic self-commodification. Our model of the networked audience assumes a many- to-many communication through which individuals conceptualize an imagined audience evoked through their tweets.},
year = {2011},
month = {Jan},
date-added = {2011-11-23 06:01:04 +0000},
date-modified = {2013-06-11 14:09:37 +0100},
pmid = {15551380582042499897related:OfuMnz6a0dcJ},
URL = {http://nms.sagepub.com/content/13/1/114.short},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Marwick/I%20tweet%20honestly%20I%20tweet%20passionately%20Twitter%20users%20context%20collapse.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p24722},
rating = {0}
}

@article{Goonatilake:2007p9397,
author = {R Goonatilake and S Hearth}, 
journal = {International Research Journal of Finance and Economics},
title = {The Volatility of the Stock Market and News},
abstract = {The volatility of stock market indicators goes beyond anyone s reasonable explanations. Industry performance, economic, and political changes are among the major factors that can affect the stock market. This paper focuses on the effect of news that surfaces throughout the day in the stock market. While there are many influences behind the constant changes in stock market performance, we can statistically analyze the influence of news on the DJIA, NASDAQ, and S{\&}P 500. From the analysis of the data collected over a ten-week period of time, we were able to conclude that there is an association between news items and the market fluctuations, measured by an increase, a decrease, or unchanged. The association between the market fluctuations of the DJIA and crude oil stock prices is adequately explored to obtain a regression model in this paper.},
number = {11},
pages = {53--64},
year = {2007},
month = {Aug},
date-added = {2011-01-25 12:09:27 +0000},
date-modified = {2013-06-11 14:54:50 +0100},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2007/Goonatilake/The%20Volatility%20of%20the%20Stock%20Market%20and%20News.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p9397},
read = {Yes},
rating = {0}
}

@article{Cataldi:2010p31272,
author = {Mario Cataldi and Luigi Di Caro and Claudio Schifanella}, 
title = {Emerging topic detection on Twitter based on temporal and social terms evaluation},
abstract = {Twitter is a user-generated content system that allows its users to share short text messages, called tweets, for a vari- ety of purposes, including daily conversations, URLs shar- ing and information news. Considering its world-wide dis- tributed network of users of any age and social condition, it represents a low level news flashes portal that, in its impres- sive short response time, has the principal advantage.
In this paper we recognize this primary role of Twitter and we propose a novel topic detection technique that permits to retrieve in real-time the most emergent topics expressed by the community. First, we extract the contents (set of terms) of the tweets and model the term life cycle according to a novel aging theory intended to mine the emerging ones. A term can be defined as emerging if it frequently occurs in the specified time interval and it was relatively rare in the past. Moreover, considering that the importance of a content also depends on its source, we analyze the social relationships in the network with the well-known Page Rank algorithm in order to determine the authority of the users. Finally, we leverage a navigable topic graph which connects the emerg- ing terms with other semantically related keywords, allowing the detection of the emerging topics, under user-specified time constraints. We provide different case studies which show the validity of the proposed approach.},
pages = {4},
year = {2010},
date-added = {2013-06-11 15:45:02 +0100},
date-modified = {2013-06-11 15:45:28 +0100},
pmid = {10073453833755738886related:BsNO7uMYzIsJ},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p31272},
rating = {0}
}

@article{Leinweber:2010p8411,
author = {D Leinweber and J Sisk}, 
title = {Relating News Analytics to Stock Returns},
abstract = {News analytics measure relevance, sentiment, novelty and volume of news. They combine natural language analysis of content, with historical and news metadata. Signals from analytics of this type have been shown to be predictive of volatility.
Aggregation and filtering of news events can also generate alpha signals for portfolio management. Filters use thresholds set using both absolute and relative measures. This detects investor behavior associated with accumulation of information and changes in sentiment.
The analytics described are used to generate investment signals. In practice, they would be combined with forecasts from other quantitative or research sources (e.g. factor, momentum, and earnings). In this paper, we analyze investment signals derived only from news, an important distinction.
Event studies on a broad universe of US equities (segmented by sector and capitalization class) are shown for the period 2003‐2008. US portfolio simulation results are shown for these signals applied over 2006‐2009. The portfolio simulation, like the event studies, is based on a ``pure news'' signal, without mixing in other quant signals, that can confuse the question of alpha from news.
Both the event studies and portfolio simulation show evidence of exploitable alpha using news analytics.},
affiliation = {CARISMA, London},
pages = {1--30},
year = {2010},
month = {Feb},
date-added = {2011-01-20 00:09:19 +0000},
date-modified = {2012-04-18 14:10:48 +0100},
URL = {http://www.optirisk-systems.com/events/carisma2010.asp},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2010/Leinweber/Relating%20News%20Analytics%20to%20Stock.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p8411},
read = {Yes},
rating = {0}
}

@article{Messias:2013p32188,
author = {J Messias and L Schmidt and R Oliveira{\ldots}}, 
journal = {First Monday},
title = {You followed my bot! Transforming robots into influential users in Twitter},
abstract = {You followed my bot! Transforming robots into influential users in Twitter.
},
year = {2013},
month = {Jan},
date-added = {2013-07-11 07:56:21 +0100},
date-modified = {2013-07-12 09:24:05 +0100},
URL = {http://ojs-prod-lib.cc.uic.edu/ojs/index.php/fm/article/view/4217},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2013/Messias/You%20followed%20my%20bot!%20Transforming%20robots%20into%20influential%20users%20in.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p32188},
rating = {0}
}

@article{Spirin:2013p24843,
author = {N Spirin}, 
title = {Mutually Reinforcing Spam Detection on Twitter and Web},
date-added = {2011-11-24 23:28:45 +0000},
date-modified = {2012-04-18 14:09:43 +0100},
pmid = {related:_pXM5Eowru0J},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/Unknown/Spirin/Mutually%20Reinforcing%20Spam%20Detection%20on%20Twitter%20and%20Web.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p24843},
read = {Yes},
rating = {0}
}

@article{Naaman:2010p23670,
author = {M Naaman and J Boase and CH Lai}, 
journal = {Proceedings of CSCW 2010},
title = {Is it really about me?: message content in social awareness streams},
abstract = {In this work we examine the characteristics of social activity and patterns of communication on Twitter, a prominent example of the emerging class of communication systems we call ``social awareness streams.'' We use system data and message content from over 350 Twitter users, applying human coding and quantitative analysis to provide a deeper understanding of the activity of individuals on the Twitter network. In particular, we develop a content-based categorization of the type of messages posted by Twitter users, based on which we examine users' activity. Our analysis shows two common types of user behavior in terms of the content of the posted messages, and exposes differences between users in respect to these activities.},
year = {2010},
month = {Jan},
date-added = {2011-10-01 14:17:31 +0100},
date-modified = {2012-04-18 14:09:13 +0100},
pmid = {17476508525031357314related:gnuUtOgHifIJ},
URL = {http://portal.acm.org/citation.cfm?id=1718918.1718953},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2010/Naaman/Is%20it%20really%20about%20me?%20message%20content%20in%20social%20awareness.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p23670},
read = {Yes},
rating = {0}
}

@article{Bryden:2013p31150,
author = {John Bryden and Sebastian Funk and Vincent Jansen}, 
journal = {EPJ Data Science},
title = {Word usage mirrors community structure in the online social network Twitter},
abstract = {Background: Language has functions that transcend the transmission of information and varies with social context. To find out how language and social network structure interlink, we studied communication on Twitter, a broadly-used online messaging service.
Results: We show that the network emerging from user communication can be structured into a hierarchy of communities, and that the frequencies of words used within those communities closely replicate this pattern. Consequently, communities can be characterised by their most significantly used words. The words used by an individual user, in turn, can be used to predict the community of which that user is a member.
Conclusions: This indicates a relationship between human language and social networks, and suggests that the study of online communication offers vast potential for understanding the fabric of human society. Our approach can be used for enriching community detection with word analysis, which provides the ability to automate the classification of communities in social networks and identify emerging social groups.},
number = {1},
pages = {1--9},
volume = {2},
year = {2013},
date-added = {2013-06-04 17:39:36 +0100},
date-modified = {2013-06-11 10:06:31 +0100},
pmid = {related:gO0q9HyhYMcJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2013/Bryden/Word%20usage%20mirrors%20community%20structure%20in%20the%20online%20social%20network.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p31150},
rating = {0}
}

@article{Macskassy:2013p28821,
author = {S.A Macskassy}, 
title = {Characterizing Retweeting Behaviors in Twitter: On the use of Text vs. Concepts},
abstract = {Twitterandothermicroblogshaverapidlybecomeasignificantmeans by which people communicate with the world and each other in near realtime. There has been a large number of studies surrounding these social media, fo- cusing on areas such as information spread, various centrality measures, topic detection and more. However, one area which has received little attention is try- ing to better understand what information is being spread and why it is being spread. One recent line of work has been looking at the problem of modeling retweeting behaviors. This work has advocated mapping tweets into a conceptual space such as Wikipedia categories and reasoning about diffusion behaviors in that space. The work, however, did not show that this was in fact needed and the question is whether one can get equally good reasoning by staying at the token or word level. This paper looks at this particular question of whether one in fact improve upon reasoning by mapping into a more abstract space or whether there is a place for token-level modeling. We show that, in fact, token-level models do have their place when reasoning about whether a tweet is likely interesting based on the tweet words but that the conceptual space is better when reasoning about homophily--similarities between users. Ideally one would like a hybrid model and we show that while the hybrid model is not always the optimal, it does yield good performance. We here repeat part of an earlier retweet study on over 768K tweet and show that profiles using a combination of word-based and concept-based fea- tures work better than either of the simpler representations.},
date-added = {2012-09-30 21:33:20 +0100},
date-modified = {2013-06-11 14:11:00 +0100},
pmid = {related:WPbgqZ4Ft9UJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/Unknown/Macskassy/Characterizing%20Retweeting%20Behaviors%20in%20Twitter%20On%20the%20use%20of%20Text.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p28821},
rating = {0}
}

@article{Weng:2011p21129,
author = {J Weng and Y Yao and E Leonardi and F Lee}, 
journal = {aaai.org},
title = {Event Detection in Twitter},
abstract = {Twitter, as a form of social media, is fast emerging in recent years. Users are using Twitter to report real-life events. This paper focuses on detecting those events by analyzing the text stream in Twitter. Although event detection has long been a research topic, the characteristics of Twitter make it a non-trivial task. Tweets reporting such events are usually overwhelmed by high flood of meaningless "babbles". Moreover, event detection algorithm needs to be scalable given the sheer amount of tweets. This paper attempts to tackle these challenges with EDCoW (Event Detection with Clustering of Wavelet-based Signals). EDCoW builds signals for individual words by applying wavelet analysis on the frequency-based raw signals of the words. It then filters away the trivial words by looking at their corresponding signal auto-correlations. The remaining words are then clustered to form events with a modularity-based graph partitioning technique. Experimental studies show promising result of EDCoW. We also present the design of a proof-of-concept system, which was used to analyze netizens' online discussion about Singapore General Election 2011.},
year = {2011},
month = {Jan},
date-added = {2011-07-12 12:35:56 +0100},
date-modified = {2012-04-18 14:10:02 +0100},
URL = {http://www.aaai.org/ocs/index.php/ICWSM/ICWSM11/paper/download/2767/3299},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Weng/Event%20Detection%20in%20Twitter.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p21129},
rating = {0}
}

@article{Kasiviswanathan:2011p25802,
author = {S Kasiviswanathan and P Melville and A Banerjee and V Sindwani}, 
journal = {Proceedings of the 20th {\ldots}},
title = {Emerging topic detection using dictionary learning},
abstract = {Streaming user-generated content in the form of blogs, microblogs, forums, and multimedia sharing sites, provides a rich source of data from which invaluable information and insights maybe gleaned. Given the vast volume of such social media data being continually generated, one of the challenges is to automatically tease apart the emerging topics of discussion from the constant background chat- ter. Such emerging topics can be identified by the appearance of multiple posts on a unique subject matter, which is distinct from previous online discourse. We address the problem of identify- ing emerging topics through the use of dictionary learning. We propose a two stage approach respectively based on detection and clustering of novel user-generated content. We derive a scalable approach by using the alternating directions method to solve the resulting optimization problems. Empirical results show that our proposed approach is more effective than several baselines in de- tecting emerging topics in traditional news story and newsgroup data. We also demonstrate the practical application to social media analysis, based on a study on streaming data from Twitter.},
year = {2011},
month = {Jan},
date-added = {2012-01-10 12:05:09 +0000},
date-modified = {2013-06-11 14:26:06 +0100},
URL = {http://dl.acm.org/citation.cfm?id=2063686},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Kasiviswanathan/Emerging%20topic%20detection%20using%20dictionary%20learning.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p25802},
rating = {0}
}

@article{Sanchez:2011p23113,
author = {H Sanchez and S Kumar}, 
journal = {users.soe.ucsc.edu},
title = {Twitter Bullying Detection},
abstract = {Data mining of Social networks is a new but interesting field within Data Mining. We leverage the power of sentiment analysis to detect bullying instances in Twitter. We are interested in understanding bullying in social networks, especially in Twitter. To best of our understanding, there is no previous work on using sentiment analysis to detect bullying instances. Our training data set consists of Twitter messages containing commonly used terms of abuse, which are considered noisy labels. These data are publicly available and can be easily retrieved by directly accessing the Twitter streaming API. For the classification of Twitter messages, also known as tweets, we use the Na{\"\i}ve Bayes classifier. It``s accuracy was close to 70% when trained with ``commonly terms of abuse'' data. The main contribution of this paper is the idea of using sentiment analysis to detect bullying instances.},
year = {2011},
date-added = {2011-09-18 11:08:07 +0100},
date-modified = {2012-04-18 14:10:16 +0100},
URL = {http://users.soe.ucsc.edu/~shreyask/ism245-rpt.pdf},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Sanchez/Twitter%20Bullying%20Detection.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p23113},
rating = {0}
}

@article{Yu:2012p27432,
author = {L Yu and S Asur and B.A Huberman}, 
journal = {Arxiv preprint arXiv:1202.0327},
title = {Artificial Inflation: The True Story of Trends in Sina Weibo},
abstract = {There has been a tremendous rise in the growth of online social networks all over the world in recent years. This has facilitated users to generate a large amount of real-time content at an incessant rate, all competing with each other to attract enough attention and become trends. While Western online social networks such as Twitter have been well studied, characteristics of the popular Chinese microblogging network Sina Weibo have not been. In this paper, we analyze in detail the temporal aspect of trends and trend-setters in Sina Weibo, constrasting it with earlier observations on Twitter. First, we look at the formation, persistence and decay of trends and examine the key topics that trend in Sina Weibo. One of our key findings is that retweets are much more common in Sina Weibo and contribute a lot to creating trends. When we look closer, we observe that a large percentage of trends in Sina Weibo are due to the continuous retweets of a small amount of fraudulent accounts. These fake accounts are set up to artificially inflate certain posts causing them to shoot up into Sina Weibo's trending list, which are in turn displayed as the most popular topics to users.},
year = {2012},
month = {Jan},
date-added = {2012-03-01 18:32:05 +0000},
date-modified = {2012-04-18 14:10:53 +0100},
URL = {http://arxiv.org/abs/1202.0327},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2012/Yu/Artificial%20Inflation%20The%20True%20Story%20of%20Trends%20in%20Sina%20Weibo.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p27432},
rating = {0}
}

@article{Tumasjan:2010p4603,
author = {A Tumasjan and TO Sprenger and PG Sandner and IM Welpe}, 
journal = {International AAAI Conference on Weblogs and Social Media, Washington, DC},
title = {Predicting elections with Twitter: What 140 characters reveal about political sentiment},
year = {2010},
date-added = {2010-12-10 21:43:33 +0000},
date-modified = {2012-04-18 14:09:27 +0100},
pmid = {1247155462894544687related:L2eEKUnJThEJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2010/Tumasjan/Predicting%20elections%20with%20Twitter%20What.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p4603},
read = {Yes},
rating = {0}
}

@article{Gonzalez:2011p18809,
author = {R Gonzalez and R Cuevas and A Cuevas and C Guerrero}, 
title = {Where are my followers? Understanding the Locality Effect in Twitter},
abstract = {Twitter is one of the most used applications in the current Internet with more than 200M accounts created so far. As other large-scale systems Twitter can obtain benefit by exploiting the Locality effect existing among its users. In this paper we perform the first comprehensive study of the Locality effect of Twitter. For this purpose we have collected the geographical location of around 1M Twitter users and 16M of their followers. Our results demonstrate that language and cultural characteristics determine the level of Locality expected for different countries. Those countries with a different language than English such as Brazil typically show a high intra-country Locality whereas those others where English is official or co-official language suffer from an exter- nal Locality effect. This is, their users have a larger number of followers in US than within their same country. This is produced by two reasons: first, US is the dominant country in Twitter counting with around half of the users, and second, these countries share a common language and cultural characteristics with US.},
year = {2011},
month = {Jan},
date-added = {2011-06-04 22:53:45 +0100},
date-modified = {2012-04-18 14:10:58 +0100},
URL = {http://arxiv.org/abs/1105.3682},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Gonzalez/Where%20are%20my%20followers?%20Understanding%20the%20Locality%20Effect%20in%20Twitter.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p18809},
rating = {0}
}

@article{Petrovic:2010p6148,
author = {S Petrovic and M Osborne and V Lavrenko}, 
journal = {Proceedings of the NAACL HLT 2010 Workshop on Computational Linguistics in a World of Social Media},
title = {The Edinburgh Twitter Corpus},
abstract = {We describe the first release of our corpus of 97 million Twitter posts. We believe that this data will prove valuable to researches working in social media, natural language processing, large-scale data processing, and similar areas.},
pages = {25},
year = {2010},
date-added = {2010-12-22 23:21:21 +0000},
date-modified = {2012-04-18 14:09:44 +0100},
pmid = {5153733775151945695related:31fdFpC9hUcJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2010/Petrovic/The%20Edinburgh%20Twitter%20Corpus.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p6148},
read = {Yes},
rating = {0}
}

@article{Yang:2012p30637,
author = {L Yang and T Sun and M Zhang and Q Mei}, 
journal = {International World Wide Web Conference Com- mittee (IW3C2)},
title = {We know what@ you{\#} tag: does the dual role affect hashtag adoption?},
abstract = {Researchers and social observers have both believed that hashtags, as a new type of organizational objects of informa- tion, play a dual role in online microblogging communities (e.g., Twitter). On one hand, a hashtag serves as a book- mark of content, which links tweets with similar topics; on the other hand, a hashtag serves as the symbol of a com- munity membership, which bridges a virtual community of users. Are the real users aware of this dual role of hash- tags? Is the dual role affecting their behavior of adopting a hashtag? Is hashtag adoption predictable? We take the initiative to investigate and quantify the effects of the dual role on hashtag adoption. We propose comprehensive mea- sures to quantify the major factors of how a user selects con- tent tags as well as joins communities. Experiments using large scale Twitter datasets prove the effectiveness of the dual role, where both the content measures and the com- munity measures significantly correlate to hashtag adoption on Twitter. With these measures as features, a machine learning model can effectively predict the future adoption of hashtags that a user has never used before.},
year = {2012},
month = {Jan},
date-added = {2013-04-14 14:35:16 +0100},
date-modified = {2013-04-14 14:38:22 +0100},
pmid = {7525170444036980016related:ML0XF6bGbmgJ},
URL = {http://dl.acm.org/citation.cfm?id=2187872},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2012/Yang/We%20know%20what@%20you%23%20tag%20does%20the%20dual%20role%20affect.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p30637},
rating = {0}
}

@article{Andre:2012p27691,
author = {P Andr{\'e} and M Bernstein and K Luther}, 
journal = {Proceedings of the ACM 2012 conference on Computer Supported Cooperative Work},
title = {Who gives a tweet?: evaluating microblog content value},
abstract = {While microblog readers have a wide variety of reactions to the content they see, studies have tended to focus on extremes such as retweeting and unfollowing. To understand the broad continuum of reactions in-between, which are typically not shared publicly, we designed a website that collected the first large corpus of follower ratings on Twitter updates. Using our dataset of over 43,000 voluntary ratings, we find that nearly 36% of the rated tweets are worth reading, 25% are not, and 39% are middling. These results suggest that users tolerate a large amount of less-desired content in their feeds. We find that users value information sharing and random thoughts above me-oriented or presence updates. We also offer insight into evolving social norms, such as lack of context and misuse of @mentions and hashtags. We discuss implications for emerging practice and tool design.},
pages = {471--474},
year = {2012},
date-added = {2012-04-24 15:00:43 +0100},
date-modified = {2013-06-11 10:06:44 +0100},
pmid = {15094236176906694364related:3K5fiNR_edEJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2012/Andr%C3%A9/Who%20gives%20a%20tweet?%20evaluating%20microblog%20content%20value.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p27691},
read = {Yes},
rating = {0}
}

@article{Samuelsson:2011p22869,
author = {M Samuelsson}, 
title = {Interaction patterns among Swedish Twitter users},
abstract = {I have in my study chosen to study about Swedish Twitter usage in the following areas usage, follow, followers, privacy, technique, writing and professional scenarios. In my pre-study a qualitative study was conducted by interviewing six persons from Sweden that actively uses Twitter about their insight into usage, follow, followers, privacy, technique, writing, professional. A quantitative study was performed by asking users 20 questions about their Twitter usage and habits. Initially I had hoped after a discussion with my supervisor Mathias Klang to receive 30 responses but received 78 responses to my survey. In these interviews it was revealed that there are no correlations in what a Swedish Twitter user Tweet. However research revealed that there are a correlation about what a user does not Tweet, personal updates since they do not feel the need to share these with others. Furthermore user does not want to use localization services on Twitter since they do not want to broadcast where they are. What is important for a user to decide if they want to follow another user is what is written in their biography since it shows info about the user. If a user Tweets too often so that it fills another users timeline, it is common that a user unfollows them since they do not see the other people that they follow in their timeline. After further research it was revealed that the two favorite Twitter clients among my interviewees and respondents to my survey is the official web client Twitter.com and TweetDeck.},
year = {2011},
month = {Jan},
date-added = {2011-09-18 11:03:29 +0100},
date-modified = {2012-04-18 14:11:00 +0100},
URL = {http://gupea.ub.gu.se/handle/2077/26703},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Samuelsson/Interaction%20patterns%20among%20Swedish%20Twitter%20users.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p22869},
rating = {0}
}

@article{Paul:2011p17129,
author = {M.J Paul and M Dredze}, 
title = {You Are What You Tweet: Analyzing Twitter for Public Health},
abstract = {Analyzing user messages in social media can mea- sure different population characteristics, including pub- lic health measures. For example, recent work has cor- related Twitter messages with influenza rates in the United States; but this has largely been the extent of mining Twitter for public health. In this work, we consider a broader range of public health applications for Twitter. We apply the recently introduced Ailment Topic Aspect Model to over one and a half million health related tweets and discover mentions of over a dozen ailments, including allergies, obesity and in- somnia. We introduce extensions to incorporate prior knowledge into this model and apply it to several tasks: tracking illnesses over times (syndromic surveillance), measuring behavioral risk factors, localizing illnesses by geographic region, and analyzing symptoms and medication usage. We show quantitative correlations with public health data and qualitative evaluations of model output. Our results suggest that Twitter has broad applicability for public health research.},
year = {2011},
date-added = {2011-04-23 01:39:20 +0100},
date-modified = {2013-06-11 13:02:25 +0100},
pmid = {15330429964017059362related:IsY9A9SgwNQJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Paul/You%20Are%20What%20You%20Tweet%20Analyzing%20Twitter%20for%20Public%20Health.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p17129},
read = {Yes},
rating = {0}
}

@article{Yi:2009p32140,
author = {Ailun Yi}, 
title = {Stock Market Prediction Based on Public Attentions: a Social Web Mining Approach},
abstract = {In this thesis, we put the problem of stock market prediction in the new context, namely, the social media. Social media is a new form of content on the Web. One of its major characteristics is the timely provision of new content and quick interaction among users. Such intensive publishing and interaction can be viewed as a measure of users attention towards a large range of topics including stock-related information. As we hold the assumption that retrieving such information timely and analysing the level of attentions in a large scale can reveal interesting relationships to the stock prices, we evaluate various methods in representing such information including simple frequency counting, loose n-gram models and noun phrase expansion. Our results showed that although the simplest counting method failed to correlate directly with stock prices, models built on more complex features that bring cross-related concepts are shown to be effective in prediction.},
year = {2009},
date-added = {2013-07-10 14:09:52 +0100},
date-modified = {2013-07-12 11:45:34 +0100},
pmid = {17103063636506419378related:sqDd8MJJWu0J},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2009/Yi/Stock%20Market%20Prediction%20Based%20on%20Public%20Attentions%20a%20Social%20Web.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p32140},
read = {Yes},
rating = {1}
}

@article{BERES:2012p29803,
author = {A BERES}, 
title = {SENTIMENT ANALYSIS FRAMEWORK ORGANIZATION BASED ON TWITTER CORPUS DATA},
abstract = {Since its inception in 2006, Twitter has gathered millions of users. They post daily tweets about news, events or conversations. These tweets express their opinion about the topic they are discussing. Twitter is a large database of content that can be semantically exploited to extract opinions and based on these opinions to classify the users. This paper presents the organization of a sentiment analysis framework based on Twitter corpus data, including crawling tweets and opinion mining of the tweets, making it easy for its users to create portfolios of trustful Twitter accounts.},
year = {2012},
date-added = {2012-10-26 12:49:40 +0100},
date-modified = {2013-07-10 09:22:28 +0100},
pmid = {related:_r-655yzpR4J},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2012/BERES/SENTIMENT%20ANALYSIS%20FRAMEWORK%20ORGANIZATION%20BASED%20ON%20TWITTER%20CORPUS%20DATA.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p29803},
rating = {0}
}

@article{Naveed:2011p20484,
author = {N Naveed and T Gottron and J Kunegis and A C Alhadi}, 
journal = {WebSci '11},
title = {Bad News Travel Fast: A Content-based Analysis of Interestingness on Twitter},
abstract = {On the microblogging site Twitter, users can forward any message they receive to all of their followers. This is called a retweet and is usually done when users find a message particularly interesting and worth sharing with others. Thus, retweets reflect what the Twitter community considers interesting on a global scale, and can be used as a function of interestingness to generate a model to describe the content-based characteristics of retweets. In this paper, we analyze a set of high- and low-level content-based features on several large collections of Twitter messages. We train a prediction model to forecast for a given tweet its likelihood of being retweeted based on its contents. From the parameters learned by the model we de- duce what are the influential content features that contribute to the likelihood of a retweet. As a result we obtain insights into what makes a message on Twitter worth retweeting and, thus, interest- ing.},
year = {2011},
month = {Jan},
date-added = {2011-06-16 12:50:19 +0100},
date-modified = {2012-04-18 14:09:13 +0100},
URL = {http://journal.webscience.org/435/},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Naveed/Bad%20News%20Travel%20Fast%20A%20Content-based%20Analysis%20of%20Interestingness%20on.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p20484},
read = {Yes},
rating = {0}
}

@article{Qiu:2011p24569,
author = {L Qiu and H Rui and A Whinston}, 
journal = {aisel.aisnet.org},
title = {A Twitter-Based Prediction Market: Social Network Approach},
abstract = {Information aggregation mechanisms are designed explicitly for collecting and aggregating dispersed information. A best example of utilizing such kind of "the wisdom of crowds" is prediction market. The purpose of our Twitter based prediction market is to suggest that carefully designed market mechanisms can elicit dispersed information, which will improve our predictions. We develop an information system that combines the power of prediction markets with the popularity of Twitter. Simulation results show that our network embedded prediction market can produce better predictions due to information exchange in social networks and outperform other non-networked prediction markets. We also demonstrate that the forecasting errors decrease with the cost of acquiring information in a network-embedded prediction market.},
year = {2011},
month = {Jan},
date-added = {2011-11-04 11:54:57 +0000},
date-modified = {2012-04-18 14:09:33 +0100},
URL = {http://aisel.aisnet.org/icis2011/proceedings/economicvalueIS/5/},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Qiu/A%20Twitter-Based%20Prediction%20Market%20Social.PDF},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p24569},
read = {Yes},
rating = {0}
}

@article{Lake:2010p18816,
author = {T Lake}, 
title = {Status Report: Twitter NLP},
abstract = {Analysis of natural language is a historically difficult tasks for computers. One could easily make the argument that the complete and accurate analysis of any piece of natural language for non-numerical information would require a class of machines which can `understand' natural language, thus such machines would need be bestowed with human like intelligence capabilities. However, the previous statement does not imply useful knowledge or behavior can not be obtained from such an endeavor without satisfying the latter condition. This paper will describe the status, methods, goals, and real world applicability of such a project.},
year = {2010},
date-added = {2011-06-04 23:00:39 +0100},
date-modified = {2012-04-18 14:09:19 +0100},
pmid = {related:JidgCuAOwdIJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2010/Lake/Status%20Report%20Twitter%20NLP.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p18816},
read = {Yes},
rating = {0}
}

@article{Tinati:2011p29814,
author = {R Tinati and L Carr and D Tarrant}, 
title = {Identifying User Types within Twitter},
abstract = {Marketing and Public Relations companies have been quick to capitalize on the use of social media to enable organizations to communicate with their current and potential future customers. Their professional experience has led them to classify individuals according to specific roles in disseminating „brand messages``. This paper describes work undertaken by the authors in conjunction with a large international public relations company to try to interpret the dissemination characteristics of Twitter users according to the dynamic properties of the pattern of messages they exchange. To enable us to do this, we have developed a model and application based upon the Twitter message exchange which enables us to analyze a number of conversations around specific topics and identify some of the key players in a conversation.},
year = {2011},
date-added = {2012-10-26 12:49:45 +0100},
date-modified = {2012-11-03 15:06:04 +0000},
pmid = {related:kFCbKJFb7BEJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Tinati/Identifying%20User%20Types%20within%20Twitter.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p29814},
rating = {0}
}

@article{Hossmann:2011p24330,
author = {T Hossmann and F Legendre and P Carta and P Gunningberg and C Rohner}, 
journal = {people.ee.ethz.ch},
title = {Twitter in Disaster Mode},
abstract = {Recent events (earthquakes, floods, etc.) have shown that users heavily rely on online social networks (OSN) to communicate and organize during disasters and in their aftermath. In this paper, we discuss what features could be added to OSN apps for smart phones -- for the example of Twitter -- to make them even more useful for disaster situations. In particular, we consider cases where the fixed communication infrastructure is partially or totally wiped out and propose to equip regular Twitter apps with a disaster mode. The disaster mode relies on opportunistic communication and epidemic spreading of Tweets from phone to phone. Such ``disaster-ready'' applications would allow to resume (although limited) communica- tion instantaneously and help distressed people to self-organize un- til regular communication networks are functioning again, or, tem- porary emergency communication infrastructure is installed.
We argue why we believe that Twitter with its simplicity and versatile features (e.g., retweet and hashtag) is a good platform to support a variety of different situations and present Twimight, our disaster ready Twitter application. In addition, we propose Twimight as a platform for disseminating sensor data providing in- formation such as locations of drinkable water sources. Eventually, we propose to rely on interest matching to scale Twitter hashtag- based searches in an opportunistic environment. The combination of these features make our opportunistic Twitter the ideal emer- gency kit in situations of disasters. We discuss and define the main implementation and research challenges (both technical and non- technical).},
year = {2011},
month = {Jan},
date-added = {2011-10-28 00:22:49 +0100},
date-modified = {2012-04-18 14:10:07 +0100},
URL = {http://people.ee.ethz.ch/~hossmath/papers/extremecom11_twimight.pdf},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Hossmann/Twitter%20in%20Disaster%20Mode.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p24330},
rating = {0}
}

@article{Mukherjee:2012p28823,
author = {S Mukherjee and P Bhattacharyya and AR Balamurali}, 
title = {Sentiment Analysis in Twitter with Lightweight Discourse Analysis},
abstract = {We propose a lightweight method for using discourse relations for polarity detection of tweets. This method is targeted towards the web-based applications that deal with noisy and unstructured text, like the tweets, and cannot afford to use heavy linguistic resources like parsing due to the frequent failure of the parsers to handle noisy data. Most of the works in micro-blogs, like Twitter, use a bag-of-words model that ignores the discourse particles like but, since, although etc. In this work, we show how connectives, modals, conditionals and negation can be used to incorporate discourse information in any bag-of-words model, to improve sentiment classification accuracy. We first give a linguistic description of the various discourse relations which leads to conditions in rules and features in SVM. Discourse relations and corresponding rules are identified with minimal processing - just a list look up. We show that our discourse-based bag-of-words model performs well in a noisy medium (Twitter), where it performs better than an existing Twitter-based application. Furthermore, we show that our approach is beneficial to structured reviews as well, where we achieve a better accuracy than a state- of-the-art system in the travel review domain. Our system compares favorably with the state-of-the-art systems and has the additional attractiveness of being less resource intensive.},
year = {2012},
date-added = {2012-09-30 21:33:20 +0100},
date-modified = {2013-07-10 09:23:37 +0100},
pmid = {related:oTla0lpytgwJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2012/Mukherjee/Sentiment%20Analysis%20in%20Twitter%20with%20Lightweight%20Discourse%20Analysis.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p28823},
read = {Yes},
rating = {0}
}

@article{Achananuparp:2012p29785,
author = {P Achananuparp and E Lim and J Jiang and Tuan-Anh Hoang}, 
journal = {ACM Transactions on Management Information Systems},
title = {Who is Retweeting the Tweeters? Modeling, Originating, and Promoting Behaviors in the Twitter Network},
abstract = {Real-time microblogging systems such as Twitter offer users an easy and lightweight means to exchange information. Instead of writing formal and lengthy messages, microbloggers prefer to frequently broadcast several short messages to be read by other users. Only when messages are interesting, are they propa- gated further by the readers. In this article, we examine user behavior relevant to information propagation through microblogging. We specifically use retweeting activities among Twitter users to define and model originating and promoting behavior. We propose a basic model for measuring the two behaviors, a mutual dependency model, which considers the mutual relationships between the two behaviors, and a range-based model, which considers the depth and reach of users' original tweets. Next, we compare the three behavior models and contrast them with the existing work on modeling influential Twitter users. Last, to demon- strate their applicability, we further employ the behavior models to detect interesting events from sudden changes in aggregated information propagation behavior of Twitter users. The results will show that the proposed behavior models can be effectively applied to detect interesting events in the Twitter stream, com- pared to the baseline tweet-based approaches.},
number = {3},
volume = {3},
year = {2012},
month = {Dec},
date-added = {2012-10-26 12:36:03 +0100},
date-modified = {2012-10-26 12:39:29 +0100},
URL = {http://dl.acm.org/citation.cfm?id=2361258},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2012/Achananuparp/Who%20is%20Retweeting%20the%20Tweeters?%20Modeling%20Originating%20and%20Promoting%20Behaviors.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p29785},
rating = {0}
}

@article{Lee:2013p31942,
author = {Kathy Lee and Ankit Agrawal and Alok Choudhary}, 
title = {Real-Time Digital Flu Surveillance using Twitter Data},
date-added = {2013-07-10 10:06:02 +0100},
date-modified = {2013-07-10 10:06:12 +0100},
pmid = {related:H_UHY2SoZVMJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/Unknown/Lee/Real-Time%20Digital%20Flu%20Surveillance%20using%20Twitter%20Data.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p31942},
rating = {0}
}

@article{Lanagan:2011p21132,
author = {J Lanagan and A.F Smeaton}, 
journal = {Proceedings of the Fifth International AAAI Conference on Weblogs and Social Media},
title = {Using Twitter to Detect and Tag Important Events in Live Sports},
abstract = {In this paper we examine the effectiveness of using a filtered stream of tweets from Twitter to automatically identify events of interest within the video of live sports transmissions. We show that using just the volume of tweets generated at any moment of a game actually provides a very accurate means of event detection, as well as an automatic method for tagging events with representative words from the tweet stream. We compare this method with an alternative approach that uses complex audio-visual content analysis of the video, showing that it provides near-equivalent accuracy for major event detection at a fraction of the computational cost. Using community tweets and discussion also provides a sense of what the audience themselves found to be the talking points of a video.},
year = {2011},
keywords = {Poster Papers}, 
date-added = {2011-07-12 12:37:32 +0100},
date-modified = {2012-04-18 14:11:05 +0100},
pmid = {related:-a55vZI11bQJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Lanagan/Using%20Twitter%20to%20Detect%20and%20Tag%20Important%20Events%20in%20Live.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p21132},
rating = {0}
}

@article{Zhao:2011p24668,
author = {X Zhao and M Yang and C Chi and M Yang}, 
journal = {cisedu.us},
title = {Twitter as a Wiki extension to support collaboration awareness},
abstract = {In our daily collaborative work, work status updates and communication about progress is usually informal, sporadic, and dispersed among different collaborators. It usually costs more to exchange informal awareness information in distributed teams. In the current study, we explored Twitter as a useful and practical extension to a wiki-based collaborative work space. We began with field interviews that investigate why and how users informally communicate about each other's work status in their current practice. Drawing from the user interviews, we developed the new system and conducted a preliminary post- evaluation for the system. Our study showed that integrating Twitter, or other existing social networking tools with a formal collaborative work space in encouraging meta-data level communication and promoting informal awareness.},
year = {2011},
date-added = {2011-11-14 08:48:14 +0000},
date-modified = {2012-04-18 14:10:31 +0100},
URL = {http://cisedu.us/storage/cts/2011/xz298_at_cornell.edu-2011.01.31-14.15.05-Zhao_CTS_2011_final.pdf},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Zhao/Twitter%20as%20a%20Wiki%20extension.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p24668},
rating = {0}
}

@article{Mizrach:2009p3367,
author = {B Mizrach and S Weerts}, 
journal = {Journal of Economic Behavior {\&} Organization},
title = {Experts online: An analysis of trading activity in a public Internet chat room},
abstract = {We analyze the trading activity in an Internet chat room over a 4-year period. The data set contains nearly 9000 trades from 676 traders. We find these traders are more skilled than retail investors analyzed in other studies. 55 percent make profits after transaction costs, and they have statistically significant  ̨ s of 0.17 percent per day after controlling for the Fama--French factors and momentum. Traders hold their winners 25 percent longer than their losers. 42 percent trade both long and short, with equal success rates, and almost double the profit per trade when short. The estimates show a strong influence from other traders, with a buy (sell) order 40.7 percent more likely to be of the same sign if there has been a recent post. Traders improve their skill over time, earning an extra {\$}189 per month for each year of trading experience. They also gain expertise in trading particular stocks. Traders who raise their Herfindahl index by 0.1 raise their profitability by {\$}46 per trade.},
pages = {266--281},
volume = {70},
year = {2009},
month = {Jan},
date-added = {2010-11-20 22:58:36 +0000},
date-modified = {2012-04-18 14:09:28 +0100},
doi = {0.1016/j.jebo.2009.02.001},
pmid = {9366625866465319531related:a5qmWpnw_IEJ},
URL = {http://linkinghub.elsevier.com/retrieve/pii/S0167268109000341},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2009/Mizrach/Experts%20online%20An%20analysis%20of.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p3367},
read = {Yes},
rating = {0}
}

@article{Huberman:2008p32184,
author = {Bernardo Huberman and Daniel Romero and Fang Wu}, 
journal = {Available at SSRN 1313405},
title = {Social networks that matter: Twitter under the microscope},
year = {2008},
date-added = {2013-07-11 07:56:01 +0100},
date-modified = {2013-07-12 09:23:42 +0100},
pmid = {15733994094641109814related:NlstTURgWtoJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2008/Huberman/Social%20networks%20that%20matter%20Twitter%20under%20the%20microscope-1.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p32184},
rating = {0}
}

@article{Perreault:2011p18811,
author = {M Perreault and D Ruths}, 
title = {The Effect of Mobile Platforms on Twitter Content Generation},
abstract = {The increased popularity of feature-rich mobile devices in recent years has enabled widespread consumption and production of social media content via mobile devices. Because mobile devices and mobile applications change context within which an individual generates and consumes microblog content, we might expect microblogging behavior to differ depending on whether the user is using a mobile device. To our knowledge, little has been established about what, if any, effects such mobile interfaces have on microblogging.
In this paper, we investigate this question within the context of Twitter, among the most popular microblogging platforms. This work makes three specific contributions. First, we quantify the ways in which user profiles are effected by the mobile context: (1) the extent to which users tend to be either fully non-mobile or mobile and (2) the relative activity of the mo- bile Twitter community. Second, we assess the differences in content between mobile and non-mobile tweets (posts to the Twitter platform). Our results show that mobile platforms produce very different patterns of Twitter usage.
As part of our analysis, we propose and apply a classification system for tweets. We consider this to be the third contribution of this work. While other classification systems have been proposed, ours is the first to permit the independent encoding of a tweet's form, content, and intended audience. In this paper we apply this system to show how tweets differ between mobile and non-mobile contexts. However, because of its flexibility and breadth, the schema may be useful to researchers studying Twitter content in other contexts as well.},
year = {2011},
date-added = {2011-06-04 22:55:17 +0100},
date-modified = {2012-04-18 14:09:27 +0100},
pmid = {related:aaj4bg4p_6EJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Perreault/The%20Effect%20of%20Mobile%20Platforms.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p18811},
read = {Yes},
rating = {0}
}

@article{Liu:2012p29845,
author = {K.L Liu and W.J Li and M Guo}, 
title = {Emoticon Smoothed Language Models for Twitter Sentiment Analysis},
abstract = {Twitter sentiment analysis (TSA) has become a hot research topic in recent years. The goal of this task is to discover the attitude or opinion of the tweets, which is typically formulated as a machine learning based text classification problem. Some methods use manually labeled data to train fully supervised models, while others use some noisy labels, such as emoticons and hashtags, for model training. In general, we can only get a limited number of training data for the fully supervised models because it is very labor-intensive and time-consuming to manually label the tweets. As for the models with noisy labels, it is hard for them to achieve satisfactory performance due to the noise in the labels although it is easy to get a large amount of data for training. Hence, the best strategy is to utilize both manually labeled data and noisy labeled data for training. However, how to seamlessly integrate these two different kinds of data into the same learning framework is still a challenge. In this paper, we present a novel model, called emoticon smoothed language model (ESLAM), to handle this challenge. The basic idea is to train a language model based on the manually labeled data, and then use the noisy emoticon data for smoothing. Experiments on real data sets demonstrate that ESLAM can effectively integrate both kinds of data to outperform those methods using only one of them.},
year = {2012},
date-added = {2012-10-26 12:49:46 +0100},
date-modified = {2012-11-03 14:58:50 +0000},
pmid = {14148834620304182483related:08z6mB_CWsQJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2012/Liu/Emoticon%20Smoothed%20Language%20Models%20for%20Twitter%20Sentiment%20Analysis.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p29845},
rating = {0}
}

@article{Burns:2009p16742,
author = {A Burns and B Eltham}, 
title = {Twitter Free Iran: an Evaluation of Twitter's Role in Public Diplomacy and Information Operations in Iran's 2009 Election Crisis},
abstract = {Social media platforms such as Twitter pose new challenges for decision-makers in an international crisis. We examine Twitter's role during Iran's 2009 election crisis using a comparative analysis of Twitter investors, US State Department diplomats, citizen activists and Iranian protestors and paramilitary forces. We code for key events during the election's aftermath from 12 June to 5 August 2009, and evaluate Twitter. Foreign policy, international political economy and historical sociology frameworks provide a deeper context of how Twitter was used by different users for defensive information operations and public diplomacy. Those who believe Twitter and other social network technologies will enable ordinary people to seize power from repressive regimes should consider the fate of Iran's protestors, some of whom paid for their enthusiastic adoption of Twitter with their lives.},
year = {2009},
date-added = {2011-04-20 21:44:05 +0100},
date-modified = {2012-04-18 14:09:31 +0100},
pmid = {3387641747214472356related:pJQAeThSAy8J},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2009/Burns/Twitter%20Free%20Iran%20an%20Evaluation.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p16742},
read = {Yes},
rating = {0}
}

@inproceedings{passant_meaning_2008,
author = {Alexandre Passant and Philippe Laublet}, 
journal = {Proceedings},
title = {Meaning Of A Tag: A collaborative approach to bridge the gap between tagging and Linked Data},
abstract = {This paper introduces MOAT, a lightweight Semantic Web framework that provides a collaborative way to let Web 2.0 content producers give meanings to their tags in a machine- readable way. To achieve this goal, this approach relies on Linked Data principles, using URIs from existing resources to define these meanings. That way, users can create inter- linked RDF data and let their content enter the Semantic Web, while solving some limits of free-tagging at the same time.},
pages = {48},
year = {2008},
date-added = {2013-04-13 21:02:22 +0100},
date-modified = {2013-06-11 13:04:29 +0100},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2008/Passant/Meaning%20Of%20A%20Tag%20A%20collaborative%20approach%20to%20bridge%20the.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p30620},
rating = {0}
}

@article{Kim:2006p9197,
author = {SM Kim and E Hovy}, 
journal = {Proceedings of the Workshop on Sentiment and Subjectivity in Text},
title = {Extracting opinions, opinion holders, and topics expressed in online news media text},
abstract = {This paper presents a method for identifying an opinion with its holder and topic, given a sentence from online news media texts. We introduce an approach of exploiting the semantic structure of a sentence, anchored to an opinion bearing verb or adjective. This method uses semantic role labeling as an intermediate step to label an opinion holder and topic using data from FrameNet. We decompose our task into three phases: identifying an opinion-bearing word, labeling semantic roles related to the word in the sentence, and then finding the holder and the topic of the opinion word among the labeled semantic roles. For a broader coverage, we also employ a clustering technique to predict the most probable frame for a word which is not defined in FrameNet. Our experimental results show that our system performs significantly better than the baseline.},
pages = {1--8},
year = {2006},
month = {Jan},
date-added = {2011-01-25 12:04:11 +0000},
date-modified = {2013-07-10 13:10:16 +0100},
pmid = {13127041526430093162related:as-q3reeLLYJ},
URL = {http://portal.acm.org/citation.cfm?id=1654642&dl=GUIDE,},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2006/Kim/Extracting%20opinions%20opinion%20holders%20and%20topics%20expressed%20in%20online%20news.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p9197},
read = {Yes},
rating = {0}
}

@article{Uskali:2009p1894,
author = {T Uskali}, 
journal = {Innovation Journalism},
title = {Weak Signals in Innovation Journalism--Cases Google, Facebook and Twitter},
year = {2009},
month = {Jan},
date-added = {2010-11-05 05:41:48 +0000},
date-modified = {2012-04-18 14:09:49 +0100},
pmid = {17958621205428348098related:wqRaZdbWOfkJ},
URL = {http://www.innovationjournalism.org/archive/injo-6-6.pdf},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2009/Uskali/Weak%20Signals%20in%20Innovation%20Journalism%E2%80%93Cases%20Google%20Facebook%20and%20Twitter.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p1894},
read = {Yes},
rating = {0}
}

@article{Doan:2011p22853,
author = {S Doan and BKH Vo and N Collier}, 
title = {An analysis of Twitter messages in the 2011 Tohoku Earthquake},
abstract = {Social media such as Facebook and Twitter have proven to be a useful resource to understand public opinion towards real world events. In this paper, we investigate over 1.5 million Twitter messages (tweets) for the period 9th March 2011 to 31st May 2011 in order to track awareness and anxiety levels in the Tokyo metropolitan district to the 2011 Tohoku Earthquake and subsequent tsunami and nuclear emergencies. These three events were tracked using both English and Japanese tweets. Preliminary results indicated: 1) close correspondence between Twitter data and earthquake events, 2) strong correlation between English and Japanese tweets on the same events, 3) tweets in the native language play an important roles in early warning, 4) tweets showed how quickly Japanese people's anxiety returned to normal levels after the earthquake event. Several distinctions between English and Japanese tweets on earthquake events are also discussed. The results suggest that Twitter data can be used as a useful resource for tracking the public mood of populations affected by natural disasters as well as an early warning system.},
year = {2011},
month = {Jan},
date-added = {2011-09-18 11:02:27 +0100},
date-modified = {2012-04-18 14:09:45 +0100},
URL = {http://arxiv.org/abs/1109.1618},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Doan/An%20analysis%20of%20Twitter%20messages%20in%20the%202011%20Tohoku%20Earthquake.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p22853},
read = {Yes},
rating = {0}
}

@article{Devitt:2007p738,
author = {A Devitt and K AHMAD}, 
journal = {Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics},
title = {Sentiment polarity identification in financial news: A cohesion-based approach},
abstract = {Text is not unadulterated fact. A text can make you laugh or cry but can it also make you short sell your stocks in company A and buy up options in company B? Research in the domain of finance strongly suggests that it can. Studies have shown that both the informational and affective aspects of news text affect the markets in profound ways, impacting on volumes of trades, stock prices, volatility and even future firm earnings. This paper aims to explore a computable metric of positive or negative polarity in financial news text which is consistent with human judgments and can be used in a quantitative analysis of news sentiment impact on financial markets. Results from a preliminary evaluation are presented and discussed.},
year = {2007},
month = {Jan},
date-added = {2010-10-30 18:25:53 +0100},
date-modified = {2013-06-11 15:24:14 +0100},
pmid = {9456404677150900046related:Tv_rofPlO4MJ},
URL = {http://acl.ldc.upenn.edu/P/P07/P07-1124.pdf},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2007/Devitt/Sentiment%20polarity%20identification%20in%20financial.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p738},
read = {Yes},
rating = {2}
}

@article{GonzalezBailon:2012p30648,
author = {Sandra Gonz{\'a}lez-Bail{\'o}n and Ning Wang and Alejandro Rivero and Javier Borge-Holthoefer and Yamir Moreno}, 
journal = {Available at SSRN 2185134},
title = {Assessing the Bias in Communication Networks Sampled from Twitter},
abstract = {We collect and analyse messages exchanged in Twitter using two of the platform's publicly available APIs (the search and stream specifications). We assess the differences between the two samples, and compare the networks of communication reconstructed from them. The empirical context is given by political protests taking place in May 2012: we track online communication around these protests for the period of one month, and reconstruct the network of mentions and re-tweets according to the two samples. We find that the search API over-represents the more central users and does not offer an accurate picture of peripheral activity; we also find that the bias is greater for the network of mentions. We discuss the implications of this bias for the study of diffusion dynamics and collective action in the digital era, and advocate the need for more uniform sampling procedures in the study of online communication.},
year = {2012},
date-added = {2013-04-16 03:02:57 +0100},
date-modified = {2013-06-11 14:55:41 +0100},
pmid = {18737548137877688related:uFC4ZLORQgAJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2012/Gonz%C3%A1lez-Bail%C3%B3n/Assessing%20the%20Bias%20in%20Communication%20Networks%20Sampled%20from%20Twitter.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p30648},
rating = {0}
}

@article{Michelson:2010p3639,
author = {M Michelson and S Macskassy}, 
journal = {AND '10: Proceedings of the fourth workshop on Analytics for noisy unstructured text data},
title = {Discovering users' topics of interest on twitter: a first look},
abstract = {Twitter, a micro-blogging service, provides users with a frame- work for writing brief, often-noisy postings about their lives. These posts are called ``Tweets.'' In this paper we present early results on discovering Twitter users' topics of inter- est by examining the entities they mention in their Tweets. Our approach leverages a knowledge base to disambiguate and categorize the entities in the Tweets. We then develop a
``topic profile,'' which characterizes users' topics of interest, by discerning which categories appear frequently and cover the entities. We demonstrate that even in this early work we are able to successfully discover the main topics of interest for the users in our study.},
year = {2010},
month = {Oct},
keywords = {user interests, Twitter}, 
date-added = {2010-11-26 16:50:28 +0000},
date-modified = {2012-04-18 14:09:19 +0100},
URL = {http://portal.acm.org/ft_gateway.cfm?id=1871852&type=pdf&coll=DL&dl=GUIDE&CFID=116090877&CFTOKEN=46873869},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2010/Michelson/Discovering%20users'%20topics%20of%20interest%20on%20twitter%20a%20first%20look.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p3639},
read = {Yes},
rating = {0}
}

@article{Xu:2013p30516,
author = {B Xu and Y Huang and H Kwak and N Contractor}, 
journal = {Proceedings of the 2013 {\ldots}},
title = {Structures of broken ties: exploring unfollow behavior on twitter},
abstract = {This study investigates unfollow behavior in Twitter, i.e. people removing others from their Twitter following lists. Considering the interdependency and dynamics of unfollow decisions, we use actor-oriented modeling (SIENA) to examine the impacts of reciprocity, status, embeddedness, homophily, and informativeness on tie dissolution. Focusing on ordinary users in tightly-knitted user groups, the results show that relational properties play key roles in the emergence of unfollow behavior: mutual following relations and common followees reduce the likelihood of unfollowing. And unfollow tends to be reciprocal: when a user is unfollowed by someone, he or she will unfollow back. However, there is no evidence of the impacts of homophily based on common interests and informativeness of interactions. The findings suggest that Twitter has many heterogeneous user groups and relational and informational factors may not be applicable universally.},
year = {2013},
month = {Jan},
date-added = {2013-03-05 11:37:16 +0000},
date-modified = {2013-03-05 11:37:28 +0000},
URL = {http://dl.acm.org/citation.cfm?id=2441875},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2013/Xu/Structures%20of%20broken%20ties%20exploring%20unfollow%20behavior%20on%20twitter.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p30516},
rating = {0}
}

@article{Zhao:2011p25819,
author = {X Zhao and J Jiang and J He and Y Song and P Achananuparp and E.P LIM and X Li}, 
title = {Topical keyphrase extraction from Twitter},
year = {2011},
date-added = {2012-01-10 12:10:05 +0000},
date-modified = {2012-04-18 14:10:05 +0100},
pmid = {7112308495087841398related:djC0xuT-s2IJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Zhao/Topical%20keyphrase%20extraction%20from%20Twitter.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p25819},
rating = {0}
}

@article{Boyd:2010p23621,
author = {D Boyd and S Golder and G Lotan}, 
journal = {HICSS-43},
title = {Tweet, Tweet, Retweet: Conversational Aspects of Retweeting on Twitter},
abstract = {Twitter---a microblogging service that enables users to post messages (``tweets'') of up to 140 characters---supports a variety of communicative practices; participants use Twitter to converse with individuals, groups, and the public at large, so when conversations emerge, they are often experienced by broader audiences than just the interlocutors. This paper examines the practice of retweeting as a way by which participants can be ``in a conversation.'' While retweeting has become a convention inside Twitter, participants retweet using different styles and for diverse reasons. We highlight how authorship, attribution, and communicative fidelity are negotiated in diverse ways. Using a series of case studies and empirical data, this paper maps out retweeting as a conversational practice.},
year = {2010},
month = {Jan},
date-added = {2011-09-29 11:39:47 +0100},
date-modified = {2013-06-11 15:56:14 +0100},
pmid = {4746353535753461140related:lB0BvWRv3kEJ},
URL = {http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.157.8632&rep=rep1&type=pdf},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2010/Boyd/Tweet%20Tweet%20Retweet%20Conversational%20Aspects%20of%20Retweeting%20on%20Twitter.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p23621},
read = {Yes},
rating = {0}
}

@article{Jansen:2009p234,
author = {B Jansen and M Zhang and K Sobel and A Chowdury}, 
journal = {JOURNAL OF THE AMERICAN SOCIETY FOR INFORMATION SCIENCE AND TECHNOLOGY},
title = {Twitter power: Tweets as electronic word of mouth},
abstract = {In this paper we report research results investigating microblogging as a form of electronic word-of-mouth for sharing consumer opinions concerning brands. We analyzed more than 150,000 microblog postings containing branding comments, sentiments, and opinions. We investigated the overall structure of these microblog postings, the types of expressions, and the movement in positive or negative sentiment. We compared automated methods of classifying sentiment in these microblogs with man- ual coding. Using a case study approach, we analyzed the range, frequency, timing, and content of tweets in a corporate account. Our research findings show that 19% of microblogs contain mention of a brand. Of the branding microblogs, nearly 20% contained some expression of brand sentiments. Of these, more than 50% were positive and 33% were critical of the company or product. Our comparison of automated and manual coding showed no significant differences between the two approaches. In analyzing microblogs for structure and composition, the linguistic structure of tweets approximate the linguistic patterns of natural language expressions. We find that microblogging is an online tool for customer word of mouth communications and discuss the implications for corporations using microblogging as part of their overall marketing strategy.},
number = {11},
pages = {2169--2188},
volume = {60},
year = {2009},
month = {Jan},
date-added = {2011-03-09 17:50:59 +0000},
date-modified = {2013-06-11 14:38:02 +0100},
pmid = {271338851922987790related:Dsuhij_9wwMJ},
URL = {http://onlinelibrary.wiley.com/doi/10.1002/asi.21149/full},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2009/Jansen/Twitter%20power%20Tweets%20as%20electronic%20word%20of%20mouth.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p14190},
read = {Yes},
rating = {0}
}

@article{Murthy:2011p24399,
author = {D Murthy and A Gross and D Oliveira}, 
journal = {Semantic Computing (ICSC)},
title = {Understanding Cancer-Based Networks in Twitter Using Social Network Analysis},
abstract = {Web-based social media networks have an increasing frequency of health-related information, resources, and networks (both support and professional). Although we are aware of the presence of these health networks, we do not yet know their ability to (1) influence the flow of health-related behaviors, attitudes, and information and (2) what resources have the most influence in shaping particular health outcomes. Lastly, the health research community lacks easy-to-use data gathering tools to conduct applied research using data from social media websites. In this position paper we discuss and sketch our current work on addressing fundamental questions about information flow in cancer-related social media networks by visualizing and understanding authority, trust, and cohesion. We discuss the development of methods to visualize these networks and information flow on them using real-time data from the social media website Twitter and how these networks influence health outcomes by examining responses to specific health messages.},
year = {2011},
month = {Jan},
date-added = {2011-10-31 23:04:41 +0000},
date-modified = {2012-04-18 14:09:24 +0100},
doi = {DOI 10.1109/ICSC.2011.51},
URL = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6061372},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Murthy/Understanding%20Cancer-Based%20Networks%20in%20Twitter%20Using%20Social%20Network%20Analysis.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p24399},
rating = {0}
}

@article{Pennacchiotti:2011p21130,
author = {M Pennacchiotti and A.M Popescu}, 
journal = {Proceedings of the Fifth International AAAI Conference on Weblogs and Social Media},
title = {A Machine Learning Approach to Twitter User Classification},
abstract = {This paper addresses the task of user classification in social media, with an application to Twitter. We auto- matically infer the values of user attributes such as po- litical orientation or ethnicity by leveraging observable information such as the user behavior, network struc- ture and the linguistic content of the user's Twitter feed. We employ a machine learning approach which relies on a comprehensive set of features derived from such user information. We report encouraging experimental results on 3 tasks with different characteristics: political affiliation detection, ethnicity identification and detect- ing affinity for a particular business. Finally, our analy- sis shows that rich linguistic features prove consistently valuable across the 3 tasks and show great promise for additional user classification needs.},
year = {2011},
keywords = {Full Technical Papers}, 
date-added = {2011-07-12 12:36:24 +0100},
date-modified = {2013-06-11 13:01:47 +0100},
pmid = {related:niRyrjQZ6pQJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Pennacchiotti/A%20Machine%20Learning%20Approach%20to%20Twitter%20User%20Classification.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p21130},
rating = {0}
}

@article{Williams:2012p29780,
author = {J Williams}, 
journal = {Proceedings of the 2012 Student Research Workshop, EMNLP2012},
title = {Extracting fine-grained durations for verbs from Twitter},
abstract = {We seek to automatically estimate typical durations for events and habits described in Twitter tweets. A corpus of more than 14 million tweets containing temporal du- ration information was collected. These tweets were classified as to their habituality status using a bootstrapped, decision tree. For each verb lemma, associated duration information was collected for episodic and habitual uses of the verb. Summary statis- tics for 483 verb lemmas and their typical habit and episode durations has been com- piled and made available. This automati- cally generated duration information is broadly comparable to hand-annotation.},
pages = {49},
year = {2012},
date-added = {2012-10-25 16:07:35 +0100},
date-modified = {2013-06-11 11:50:03 +0100},
pmid = {related:XFyMUXyrE6EJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2012/Williams/Extracting%20fine-grained%20durations%20for%20verbs%20from%20Twitter.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p29780},
rating = {0}
}

@article{Grosseck:2008p1905,
author = {G Grosseck and C Holotescu}, 
journal = {4th International Scientific Conference},
title = {Can we use Twitter for educational activities},
abstract = {Twitter is the most popular microblogging application, with almost one million users called twitterers, who can send and receive messages via the web, SMS, instant messaging clients, and by third party applications. Posts are limited to 140 text characters in length. With a solid experience in using Web2.0 technologies in education, the authors are trying to provide arguments for using Twitter as microblogging platform / social network in education, underlining its advantages, but also possible bad points. The article also presents an application related to the Romanian Twitosphere and a Romanian microblogging platform, already used in education.},
year = {2008},
month = {Jan},
date-added = {2010-11-05 05:43:11 +0000},
date-modified = {2012-04-18 14:09:13 +0100},
pmid = {4408977932747352368related:MCnx7xHWLz0J},
URL = {http://www.morsmal.org/documents/members/admin/Can-we-use-Twitter-for-educational-activities.pdf},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2008/Grosseck/Can%20we%20use%20Twitter%20for%20educational%20activities.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p1905},
read = {Yes},
rating = {0}
}

@article{Diakopoulos:2010p2501,
author = {NA Diakopoulos and DA Shamma}, 
journal = {Proceedings of the 28th international conference on Human factors in computing systems},
title = {Characterizing debate performance via aggregated twitter sentiment},
abstract = {Television broadcasters are beginning to combine social micro-blogging systems such as Twitter with television to create social video experiences around events. We looked at one such event, the first U.S. presidential debate in 2008, in conjunction with aggregated ratings of message sentiment from Twitter. We begin to develop an analytical methodology and visual representations that could help a journalist or public affairs person better understand the temporal dynamics of sentiment in reaction to the debate video. We demonstrate visuals and metrics that can be used to detect sentiment pulse, anomalies in that pulse, and indications of controversial topics that can be used to inform the design of visual analytic systems for social media events.},
pages = {1195--1198},
year = {2010},
date-added = {2010-11-08 14:24:50 +0000},
date-modified = {2013-06-11 15:23:40 +0100},
pmid = {4005835765017006714related:etJkimeWlzcJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2010/Diakopoulos/Characterizing%20debate%20performance%20via%20aggregated%20twitter%20sentiment.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p2501},
read = {Yes},
rating = {0}
}

@article{Zhang:2009p1618,
author = {W B Zhang and S Skiena}, 
journal = {2009 IEEE/WIC/ACM International COnference on Web Intelligence and Intelligent Agent Technology},
title = {Improving movie gross prediction through news analysis},
abstract = {Traditional movie gross predictions are based on numerical and categorical movie data from The Internet Movie Database (IMDB). In this paper, we use the quantitative news data generated by Lydia, our system for large-scale news analysis, to help people to predict movie grosses. By analyzing two different models (regression and k-nearest neighbor models), we find models using only news data can achieve similar performance to those using IMDB data. Moreover, we can achieve better performance by using the combination of IMDB data and news data. Further, the improvement is statistically significant.},
year = {2009},
month = {Jan},
date-added = {2010-11-03 12:11:28 +0000},
date-modified = {2013-06-11 11:16:49 +0100},
pmid = {3093724479652497155related:Awee4gUe7yoJ},
URL = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=5286056},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2009/Zhang/Improving%20movie%20gross%20prediction%20through%20news%20analysis.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p1618},
read = {Yes},
rating = {0}
}

@article{Inouye:2010p6297,
author = {D Inouye}, 
title = {Multiple Post Microblog Summarization},
abstract = {The use of microblogs such as Twitter1 has increased incredibly over the past few years. Because of the public nature and sheer volume of text from these constantly changing mi- croblogs, it is often difficult to fully understand what is being said about various topics. A method for summarizing popular topics of microblogs has been proposed but its summaries are only one sentence or phrase in length. Therefore, this work focuses on extending microblog summarization by producing multiple post summaries. Two main summarization algorithms are explored: a clustering based algorithm and a threshold based Hybrid TF-IDF algorithm. The results will be evaluated by comparing the generated summaries with manually generated summaries. For purposes of comparison, the results are also compared to MEAD, LexRank and TextRank---some leading traditional multi- document summarization systems.},
year = {2010},
date-added = {2010-12-27 00:20:33 +0000},
date-modified = {2012-04-18 14:09:47 +0100},
pmid = {related:5gxWadcYyzEJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2010/Inouye/Multiple%20Post%20Microblog%20Summarization.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p6297},
rating = {0}
}

@article{Lauschke:2012p29848,
author = {C Lauschke and E Ntoutsi}, 
journal = {isl.cs.unipi.gr
},
title = {Monitoring User Evolution in Twitter},
abstract = {Nowadays social media are widely used for the broadcasting of different types of information, such as events, activities and opinions. Analyzing this vast amount of data for extracting models that describe individual users or groups of users has gained a lot of attention lately. In this work we analyze individual users and monitor changes in their published content over time. We propose a topic-based user profiling and monitoring approach for change detection and monitoring of profile evolution. Our method is capable of detecting persistent topics representing long term interests of the user as well as short term topics that refer to everyday events or reactions to the news. We evaluate our approach on real data from Twitter.},
year = {2012},
date-added = {2012-11-03 05:19:43 +0000},
date-modified = {2012-11-03 05:50:56 +0000},
URL = {http://isl.cs.unipi.gr/people/ntoutsi/papers/12.BASNA.pdf},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2012/Lauschke/Monitoring%20User%20Evolution%20in%20Twitter.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p29848},
rating = {0}
}

@article{MorellJr:2012p29798,
author = {D Morell Jr}, 
journal = {rave.ohiolink.edu
},
title = {Visualizing and Characterizing Real World Events on Twitter},
abstract = {Mass amounts of data exist on social media networks, much of which has been used to analyze brand performance. As has been reported in the popular press, social media is increasingly being used to share information in times of social and political uprising. In this research, we have developed new methods for visualizing and characterizing the emergence of events using the data available on social networks. We have developed methods to cluster Twitter posts in real-time using a number of different criteria as well as a web service to facilitate creation of mashups using posts and clusters we have captured. As a demonstration, we have created an iPad application with custom visuals designed to characterize these events. Our research contributes new analysis methods along with usable tools to assist future work in this developing research area.},
year = {2012},
month = {Dec},
date-added = {2012-10-26 12:49:49 +0100},
date-modified = {2013-06-11 13:13:20 +0100},
URL = {http://rave.ohiolink.edu/etdc/view?acc_num=miami1340734887},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2012/Morell%20Jr/Visualizing%20and%20Characterizing%20Real%20World%20Events%20on%20Twitter.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p29798},
rating = {0}
}

@article{Asur:2011p20634,
author = {S Asur and B.A Huberman and G Szabo and C Wang}, 
title = {Trends in Social Media: Persistence and Decay},
year = {2011},
date-added = {2011-06-27 16:50:57 +0100},
date-modified = {2012-04-18 14:09:39 +0100},
pmid = {related:yGWX0YNs18IJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Asur/Trends%20in%20Social%20Media%20Persistence.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p20634},
rating = {0}
}

@article{Earle:2012p27419,
author = {P Earle and DC Bowden and M Guy}, 
journal = {Annals of Geophysics},
title = {Twitter earthquake detection: earthquake monitoring in a social world},
abstract = {The U.S. Geological Survey (USGS) is investigating how the social networking site Twitter, a popular service for sending and receiving short, public text messages, can augment USGS earthquake response products and the delivery of hazard information. Rapid detection and qualitative assessment of shaking events are possible because people begin sending public Twitter messages (tweets) with in tens of seconds after feeling shaking. Here we present and evaluate an earthquake detection procedure that relies solely on Twitter data. A tweet-frequency time series constructed from tweets containing the word ``earthquake'' clearly shows large peaks correlated with the origin times of widely felt events. To identify possible earthquakes, we use a short-term-average, long-term-average algorithm. When tuned to a moderate sensitivity, the detector finds 48 globally- distributed earthquakes with only two false triggers in five months of data. The number of detections is small compared to the 5,175 earthquakes in the USGS global earthquake catalog for the same five-month time period, and no accurate location or magnitude can be assigned based on tweet data alone. However, Twitter earthquake detections are not without merit. The detections are generally caused by widely felt events that are of more immediate interest than those with no human impact. The detections are also fast; about 75% occur within two minutes of the origin time. This is considerably faster than seismographic detections in poorly instrumented regions of the world. The tweets triggering the detections also provided very short first-impression narratives from people who experienced the shaking.},
year = {2012},
month = {Jan},
date-added = {2012-02-24 21:42:19 +0000},
date-modified = {2012-04-18 14:09:21 +0100},
URL = {http://www.annalsofgeophysics.eu/index.php/annals/article/view/5364},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2012/Earle/Twitter%20earthquake%20detection%20earthquake%20monitoring.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p27419},
rating = {0}
}

@article{Plotkowiak:2011p23352,
author = {T Plotkowiak and K Stanoeveka-Slabeva}, 
journal = {asna.ch},
title = {Information Diffusion in Twitter Communities},
abstract = {Social scientists have long recognized the importance of social networks in the spread of information (Granovetter, 1973) and innovation (Rogers, 1995). Modern communications technologies, notably email and more recently social media, have only enhanced the role of networks in marketing (Domingos {\&} Richardson, 2001), information dissemination (Gruhl, Guha, Liben--‐‑Nowell, {\&} Tomkins, 2004; Wu {\&} Huberman, 2004) or search (Adar, Zhang, Adamic, {\&} Lukose, 2004a) . The new emerging network data offers a rich source of evidence for studying the structure of social networks (Leskovec {\&} Horvitz, 2008) and the dynamics of individual and group behavior (Lerman, 2007).
Yet in most studies, the structure of the underlying network was not directly visible but had to be inferred from the flow of information from one individual to another. The same held for the different forms of interactions of users or the strength of their connection with each other. Finally the actual diffusion of information was mostly also not visible but had also to be inferred. This posed a serious challenge to our efforts to understand how the structure of the network affects dynamics of information spread on it. In contrast to the historical hindrances the homogenous medium of Twitter allows us to study how individuals embed themselves in a social medium. With whom they interact in which form (@--‐‑replies, direct messages, etc.) allows us to observe the actual information diffusion in form of retweets.
Another shortcoming in existing information diffusion studies is that although a vast body of literature explains the diffusion of information in cohesive groups, there are only few studies that have analysed multiple groups and communities at the same time and studied the diffusion of information between bigger communities. The community has always either remained the outer cover of the data collection and has so created the framework for each study or it perished completely as a structural component when information diffusion has been studied for the whole population (Adar, Zhang, Adamic, {\&} Lukose, 2004b; Leskovec, McGlohon, Faloutsos, Glance, {\&} Hurst, 2007). Yet it is explicitly this "ʺmeso"ʺ --‐‑ level of analysis, which describes different communities with their members and roles that allow for interesting insights into the mechanics information diffusion inside and between cohesive groups. For example an idea or innovation can arise in one community and then spread
throughout this community with the help of opinion leaders or be transported to another community with the help of brokers between those communities.
We argue that Twitter users embed themselves different topic groups (Byrne, 1971; Turner, Smith, Fisher, {\&} Welser, 2005), where not the attributes of the actor and his profile decide about his interest but rather whom he follows and whom he interacts with. As a consequence of this fuzzy membership in a homogenous medium the individual is embedded in an ecosystem of topic communities, which compete for his attention. The study of such communities presents a very fruitful ground in order to analyse the information diffusion between such communities, which has not yet been studied before.
The third issue we want to address in this paper are the existing role concepts in literature that describe how certain roles in populations can significantly influence the diffusion of information (Bass, 2004; Gladwell, 2000; Katz {\&} Lazarsfeld, 1955; Lazarsfeld, Berelson, {\&} Gaudet, 1968; Merton, 1968; Schenk, 1993; Valente, 1993; Weinmann, 1994) or information (R. Burt, 1995). The current theory and methods for the identification of such roles, do often lack to address the issue if their potential influence might only be limited to their own community. In our described topic communities, it we therefore address the question how actors with a strong structural position are involved in diffusion processes and if their role inside the community plays an part in the diffusion of information inside and across different communities. Similar to opinion leaders we are asking the same question for structural brokers (Ronald S Burt, 2010) in online communities: If the population is fragmented like in our case into multiple topic communities, we want to ask if topic brokers that facilitate the information diffusion between certain communities, or if their influence is marginal.},
year = {2011},
date-added = {2011-09-27 09:17:54 +0100},
date-modified = {2013-06-11 13:00:12 +0100},
URL = {http://www.asna.ch/fileadmin/user_upload/2011/Abstracts2011/PlotkowiakStanoevska.pdf},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Plotkowiak/Information%20Diffusion%20in%20Twitter%20Communities.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p23352},
rating = {0}
}

@article{Dilrukshi:2013p30961,
author = {I Dilrukshi and K De Zoysa and A Caldera}, 
journal = {djks123.cn
},
title = {Twitter News Classification Using SVM},
abstract = {Social Networks, many news providers used to share their news headlines in various web sites and web blogs. Now-a-days in Sri Lanka, there are many news groups whom share their news headlines in micro blogging services such as Twitter . These data may carry out ... 
},
date-added = {2013-05-08 18:10:04 +0100},
date-modified = {2013-05-08 18:13:02 +0100},
URL = {http://www.djks123.cn/ieee_cd/data/papers/12184.pdf},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/Unknown/Dilrukshi/Twitter%20News%20Classification%20Using%20SVM.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p30961},
rating = {0}
}

@article{Morstatter:2013p30599,
author = {F Morstatter and J {\"u}rgen Pfeffer and H Liu and K Carley}, 
journal = {public.asu.edu
},
title = {Is the Sample Good Enough? Comparing Data from Twitter's Streaming API with Twitter's Firehose},
abstract = {Twitter is a social media giant famous for the exchange of short, 140-character messages called ``tweets''. In the scientific community, the microblogging site is known for openness in sharing its data. It provides a glance into its millions of users and billions of tweets through a ``Streaming API'' which provides a sample of all tweets matching some parameters preset by the API user. The API service has been used by many researchers, companies, and governmental institutions that want to extract knowledge in accordance with a diverse array of questions pertaining to social media. The essential drawback of the Twitter API is the lack of documentation concerning what and how much data users get. This leads researchers to question whether the sampled data is a valid representation of the overall activity on Twitter. In this work we embark on answering this question by comparing data collected using Twitter's sampled API service with data collected using the full, albeit costly, Firehose stream that includes every single published tweet. We compare both datasets using common statistical metrics as well as metrics that allow us to compare topics, networks, and locations of tweets. The results of our work will help researchers and practitioners understand the implications of using the Streaming API.},
year = {2013},
month = {Jan},
date-added = {2013-04-04 06:37:46 +0100},
date-modified = {2013-06-11 10:01:51 +0100},
URL = {http://www.public.asu.edu/~huanliu/papers/icwsm13.pdf},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2013/Morstatter/Is%20the%20Sample%20Good%20Enough?%20Comparing%20Data%20from%20Twitter's%20Streaming.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p30599},
rating = {0}
}

@article{Earle:2010p4643,
author = {P Earle and M Guy and Richard Buckmaster and C Ostrum and S Horvath and A Vaughan}, 
journal = {Seismological Research Letters},
title = {OMG Earthquake! Can Twitter improve earthquake response?},
number = {2},
pages = {246},
volume = {81},
year = {2010},
date-added = {2010-12-11 07:19:03 +0000},
date-modified = {2012-04-18 14:09:23 +0100},
pmid = {5461972789716657324related:rCTpP1DTzEsJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2010/Earle/OMG%20Earthquake!%20Can%20Twitter%20improve.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p4643},
read = {Yes},
rating = {0}
}

@article{Wang:2012p29808,
author = {W Wang and L Chen and K Thirunarayan and A.P Sheth}, 
title = {Harnessing Twitter `Big Data'for Automatic Emotion Identification},
abstract = {User generated content on Twitter (produced at an enormous rate of 340 million tweets per day) provides a rich source for gleaning people's emotions, which is necessary for deeper understanding of people's behaviors and actions. Extant studies on emotion identification lack comprehensive coverage of ``emotional situations'' because they use relatively small training datasets. To overcome this bottleneck, we have automatically cre- ated a large emotion-labeled dataset (of about 2.5 million tweets) by harnessing emotion-related hashtags available in the tweets. We have applied two different machine learning algorithms for emotion identification, to study the effectiveness of various feature combinations as well as the effect of the size of the training data on the emotion identification task. Our experiments demonstrate that a combination of unigrams, bigrams, sentiment/emotion- bearing words, and parts-of-speech information is most effective for gleaning emotions. The highest accuracy (65.57%) is achieved with a training data containing about 2 million tweets.},
year = {2012},
date-added = {2012-10-26 12:49:45 +0100},
date-modified = {2012-11-03 15:07:31 +0000},
pmid = {related:NrjXa9WPLWQJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2012/Wang/Harnessing%20Twitter%20%E2%80%98Big%20Data%E2%80%99for%20Automatic%20Emotion%20Identification.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p29808},
rating = {0}
}

@article{Saito:2013p30832,
author = {Kodai Saito and Naoki Masuda}, 
journal = {arXiv preprint arXiv:1302.0677},
title = {Two types of Twitter users with equally many followers},
abstract = {The number of followers is acknowledged as the pre- sumably most basic popularity measure of Twitter users. However, because it is subjected to manipula- tions and therefore may be deceptive, some alternative methods for ranking Twitter users that take into account users' activities such as the tweet and retweet rate have been proposed. In the present work, we take a purely network approach to this fundamental question. First of all, we show that there are two types of users possess- ing a large number of followers. The first type of user follows a small number of others. The second type of user follows almost as equally many others as the num- ber of its followers. Such a distinction is prominent for Japanese, Russian, and Korean users among the seven language groups that we examined. Then, we compare local (i.e., egocentric) followership networks around the two types of users with many followers. We show that the latter type, which is presumably uninfluential users despite its large number of followers, is characterized by high link reciprocity, large clustering coefficient, a large fraction of the second type of users among the fol- lowers, and a small PageRank. We conclude that the number of others that a user follows is as equally im- portant as the number of followers when estimating the importance of a user in the Twitter blogosphere.},
year = {2013},
date-added = {2013-04-25 14:57:22 +0100},
date-modified = {2013-06-11 12:25:35 +0100},
pmid = {related:yHKaNIFpRfEJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2013/Saito/Two%20types%20of%20Twitter%20users%20with%20equally%20many%20followers.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p30832},
rating = {0}
}

@article{Petrovic:2013p31134,
author = {Sasa Petrovic and Miles Osborne and Victor Lavrenko}, 
journal = {Arxiv},
title = {I Wish I Didn't Say That! Analyzing and Predicting Deleted Messages in Twitter},
abstract = {Twitter has become a major source of data for social media researchers. One important aspect of Twitter not previously considered are {\em deletions} - removal of tweets from the stream. Deletions can be due to a multitude of reasons such as privacy concerns, rashness or attempts to undo public statements. We show how deletions can be automatically predicted ahead of time and analyse which tweets are likely to be deleted and how.},
eprint = {1305.3107v1},
volume = {cs.SI},
year = {2013},
month = {May},
keywords = {cs.CL, cs.SI}, 
date-added = {2013-06-04 16:15:10 +0100},
date-modified = {2013-06-11 09:49:31 +0100},
pmid = {1305.3107v1},
URL = {http://arxiv.org/abs/1305.3107v1},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2013/Petrovic/I%20Wish%20I%20Didn't%20Say%20That!%20Analyzing%20and%20Predicting%20Deleted.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p31134},
rating = {0}
}

@article{Anonymous:2010p2549,
title = {twitter 2bn},
pages = {1--10},
year = {2010},
month = {Nov},
date-added = {2010-11-08 14:59:15 +0000},
date-modified = {2012-04-18 14:09:19 +0100},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2010/Unknown/twitter%202bn.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p2549},
read = {Yes},
rating = {0}
}

@article{Singh:2010p3643,
author = {VK Singh and R Jain}, 
journal = {Proceedings of the 19th international conference on World wide web},
title = {Structural analysis of the emerging event-web},
abstract = {Events are the fundamental abstractions to study the dynamic world. We believe that the next generation of web (i.e. event-web), will focus on interconnections between events as they occur across space and time [3]. In fact we argue that the real value of large volumes of microblog data being created daily lies in its inherent spatio- temporality, and its correlation with the real-world events. In this context, we studied the structural properties of a corpus of 5,835,237 Twitter microblogs, and found it to exhibit Power laws across space and time, much like those exhibited by events in multiple domains. The properties studied over microblogs on different topics can be applied to study relationships between related events, as well as data organization for event-based, real-time, and location-aware applications.},
pages = {1183--1184},
year = {2010},
date-added = {2010-11-26 16:55:15 +0000},
date-modified = {2012-04-18 14:10:04 +0100},
pmid = {related:-psKGtuzjioJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2010/Singh/Structural%20analysis%20of%20the%20emerging.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p3643},
read = {Yes},
rating = {0}
}

@article{Choy:2012p28377,
author = {M Choy}, 
journal = {Arxiv preprint arXiv:1205.6396},
title = {Effective Listings of Function Stop words for Twitter},
abstract = {Many words in documents recur very frequently but are essentially meaningless as they are used to join words together in a sentence. It is commonly understood that stop words do not contribute to the context or content of textual documents. Due to their high frequency of occurrence, their presence in text mining presents an obstacle to the understanding of the content in the documents. To eliminate the bias effects, most text mining software or approaches make use of stop words list to identify and remove those words. However, the development of such top words list is difficult and inconsistent between textual sources. This problem is further aggravated by sources such as Twitter which are highly repetitive or similar in nature. In this paper, we will be examining the original work using term frequency, inverse document frequency and term adjacency for developing a stop words list for the Twitter data source. We propose a new technique using combinatorial values as an alternative measure to effectively list out stop words.},
year = {2012},
month = {Jan},
date-added = {2012-06-06 12:46:36 +0100},
date-modified = {2012-07-14 13:24:30 +0100},
URL = {http://arxiv.org/abs/1205.6396},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2012/Choy/Effective%20Listings%20of%20Function%20Stop%20words%20for%20Twitter.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p28377},
rating = {0}
}

@article{Squires:2011p24216,
author = {D Squires}, 
journal = {cs.uiowa.edu},
title = {Twitter Misinformation},
abstract = {How accurate are studies that try to depict the arrangement of users on social networks? Is there a possible way to determine whom is leading the way according to emerging topics on websites such as Twitter? This subject of this research will delve into the misconceptions about age, social media, and what is the driving force behind emerging topics on social networks such as Twitter. I believe there is a general misdirection given by statistic providers which can be supported by asking oneself why they would stack their data to favor one group of people over another.},
year = {2011},
date-added = {2011-10-06 15:16:20 +0100},
date-modified = {2012-04-18 14:10:38 +0100},
URL = {https://www.cs.uiowa.edu/~dsquires/webminingproject/web_mining_project.pdf},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Squires/Twitter%20Misinformation.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p24216},
rating = {0}
}

@article{Spina:2011p21404,
author = {D Spina and E Amig{\'o} and J Gonzalo}, 
title = {Filter keywords and majority class strategies for company name disambiguation in Twitter},
abstract = {Monitoring the online reputation of a company starts by retrieving all (fresh) information where the company is mentioned; and a major problem in this context is that company names are often ambiguous (apple may refer to the company, the fruit, the singer, etc.). The problem is particularly hard in microblogging, where there is little context to disambiguate: this was the task addressed in the WePS-3 CLEF lab exercise in 2010. This paper introduces a novel fingerprint representation technique to visualize and compare system results for the task. We apply this technique to the systems that originally participated in WePS-3, and then we use it to explore the usefulness of filter keywords (those whose presence in a tweet reliably signals either the positive or the negative class) and finding the majority class (whether positive or negative tweets are predominant for a given company name in a tweet stream) as signals that contribute to address the problem. Our study shows that both are key signals to solve the task, and we also find that, remarkably, the vocabulary associated to a company in the Web does not seem to match the vocabulary used in Twitter streams: even a manual extraction of filter keywords from web pages has substantially lower recall than an oracle selection of the best terms from the Twitter stream.},
year = {2011},
date-added = {2011-07-30 21:51:54 +0100},
date-modified = {2012-04-18 14:10:06 +0100},
URL = {http://nlp.uned.es/~damiano/pdf/spina2011filterkeywords.pdf},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Spina/Filter%20keywords%20and%20majority%20class.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p21404},
rating = {0}
}

@article{Johnes:2013p31143,
author = {G Johnes}, 
journal = {Higher Education Review},
title = {Tweet sensations: investigating the potential use of sentiment analysis in higher education in the UK},
abstract = {Online social networking sites offer a rich data set which can be used by organisations to enhance their understanding of how stakeholders form their opinions about the organisation's offerings. Using data about British universities collected from twitter, this paper reports the results obtained by conducting a sentiment analysis, and suggests ways in which universities could benefit from such analyses.},
year = {2013},
month = {Jan},
date-added = {2013-06-04 17:22:23 +0100},
date-modified = {2013-06-11 10:03:45 +0100},
URL = {http://eprints.lancs.ac.uk/id/eprint/64605},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2013/Johnes/Tweet%20sensations%20investigating%20the%20potential%20use%20of%20sentiment%20analysis%20in.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p31143},
rating = {0}
}

@article{DeCristofaro:2013p25572,
author = {E De Cristofaro and C Soriente and G Tsudik and A Williams}, 
journal = {eprint.iacr.org},
title = {Hummingbird: Privacy at the time of Twitter},
abstract = {In the last several years, micro-blogging Online Social Networks (OSNs), such as Twitter, have taken the world by storm, now boasting over 100 million subscribers. As an unparalleled stage for an enor- mous audience, they offer fast and reliable centralized diffusion of pithy tweets to great multitudes of information-hungry and always-connected followers. At the same time, this information gathering and dissemination paradigm prompts some important privacy concerns pertaining to relationships between tweeters and followers and interests of the latter.
In this paper, we assess the loss of privacy in today's Twitter-like OSNs and describe an architecture and a trial implementation of a privacy-preserving service called Hummingbird. It is essentially a varia- tion of Twitter that protects tweet contents, hashtags and follower interests from the (potentially) prying eyes of the centralized server. We argue that, although inherently limited by Twitter's mission of scal- able information-sharing, this degree of privacy is valuable. We demonstrate, via a working prototype, that its additional costs are tolerably low. We also sketch out some viable enhancements that might offer even better privacy in the long term.},
date-added = {2012-01-01 19:50:23 +0000},
date-modified = {2012-04-18 14:09:35 +0100},
URL = {http://eprint.iacr.org/2011/640.pdf},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/Unknown/De%20Cristofaro/Hummingbird%20Privacy%20at%20the%20time.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p25572},
rating = {0}
}

@article{Williams:2012p28367,
author = {J Williams and G Katz}, 
journal = {lrec-conf.org
},
title = {A New Twitter Verb Lexicon for Natural Language Processing},
abstract = {We describe in-progress work on the creation of a new lexical resource that contains a list of 486 verbs annotated with quantified temporal durations for the events that they describe. This resource is being compiled from more than 14 million tweets from the Twitter microblogging site. We are creating this lexicon of verbs and typical durations to address a gap in the available information that is represented in existing research. The data that is contained in this lexicon is unlike any existing resources, which have been traditionally comprised of literature excerpts, news stories, and full-length weblogs. This kind of knowledge about how long an event lasts is crucial for natural language processing and is especially useful when the temporal duration of an event is implied. We are using data from Twitter because Twitter is a rich resource since people are publicly posting real events and real durations of those events throughout the day.},
year = {2012},
date-added = {2012-06-06 12:46:36 +0100},
date-modified = {2012-07-14 12:44:04 +0100},
URL = {http://www.lrec-conf.org/proceedings/lrec2012/pdf/1076_Paper.pdf},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2012/Williams/A%20New%20Twitter%20Verb%20Lexicon%20for%20Natural%20Language%20Processing.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p28367},
read = {Yes},
rating = {0}
}

@article{Altman:2012p29802,
author = {E Altman and Y Portilla}, 
title = {Geo-linguistic fingerprint and the evolution of languages in Twitter},
abstract = {Having access to content of messages sent by some given group of subscribers of a social network may be used to identify (and quantify) some features of that group. The feature can stand for the level of interest in some event or product, or for the popularity of some idea, or a musical hit or of a political figure. The feature can also stand for the way the written language is used and transformed, the way words are spelled and the way new grammatical rules appear. This paper has two goals. First, we identify features of groups of subscribers that have their geographic location and their language in common. We develop a methodology that allows one to perform such a study using freely available statistical tools which makes use of a part of all tweets which Twitter makes available for free over the Internet. The methodology is based on the fact that one can differentiate among some geographic areas according to the activity pattern of tweets during the time of the day. The second objective is to present our findings on the way spelling and new words have are used in Twitter. We analyze differences in appearance of new spellings among communities that are characterized by different locations but have a common language.},
year = {2012},
date-added = {2012-10-26 12:49:46 +0100},
date-modified = {2012-11-03 14:57:29 +0000},
pmid = {related:sZZbBTZ9EyQJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2012/Altman/Geo-linguistic%20fingerprint%20and%20the%20evolution%20of%20languages%20in%20Twitter.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p29802},
rating = {0}
}

@article{Zhao:2011p27415,
author = {W Zhao and J Jiang and J Weng and J He and E.P LIM and H Yan and X Li}, 
journal = {Advances in Information Retrieval},
title = {Comparing Twitter and traditional media using topic models},
abstract = {Twitter as a new form of social media can potentially con- tain much useful information, but content analysis on Twitter has not been well studied. In particular, it is not clear whether as an information source Twitter can be simply regarded as a faster news feed that covers mostly the same information as traditional news media. In This paper we empirically compare the content of Twitter with a traditional news medium, New York Times, using unsupervised topic modeling. We use a Twitter-LDA model to discover topics from a representative sample of the entire Twitter. We then use text mining techniques to compare these Twitter topics with topics from New York Times, taking into considera- tion topic categories and types. We also study the relation between the proportions of opinionated tweets and retweets and topic categories and types. Our comparisons show interesting and useful findings for down- stream IR or DM applications.},
pages = {338--349},
year = {2011},
date-added = {2012-02-24 21:42:18 +0000},
date-modified = {2012-04-18 14:10:43 +0100},
pmid = {14511381248510863065related:2SbBZVzIYskJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Zhao/Comparing%20Twitter%20and%20traditional%20media.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p27415},
rating = {0}
}

@article{Petrovic:2010p1719,
author = {S Petrovic and M Osborne and V Lavrenko}, 
journal = {Proceedings of NAACL},
title = {Streaming first story detection with application to twitter},
abstract = {With the recent rise in popularity and size of social media, there is a growing need for systems that can extract useful information from this amount of data. We address the problem of detecting new events from a stream of Twitter posts. To make event detection feasible on web-scale corpora, we present an algorithm based on locality-sensitive hashing which is able overcome the limitations of traditional approaches, while maintaining competitive results. In particular, a comparison with a state-of-the-art system on the first story detection task shows that we achieve over an order of magnitude speedup in processing time, while retaining comparable performance. Event detection experiments on a collection of 160 million Twitter posts show that celebrity deaths are the fastest spreading news on Twitter.},
year = {2010},
month = {Jan},
date-added = {2010-11-04 10:04:06 +0000},
date-modified = {2012-04-18 14:10:04 +0100},
pmid = {13397102747599327100related:fE8R0vcR7LkJ},
URL = {http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.170.9438&rep=rep1&type=pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p1719},
read = {Yes},
rating = {0}
}

@article{Kwak:2011p16223,
author = {H Kwak and H Chun and S Moon}, 
journal = {an.kaist.ac.kr},
title = {Fragile Online Relationship: A First Look at Unfollow Dynamics in Twitter},
abstract = {We analyze the dynamics of the behavior known as `unfollow' in Twitter. We collected daily snapshots of the online relationships of 1.2 million Korean-speaking users for 51 days as well as all of their tweets. We found that Twit- ter users frequently unfollow. We then discover the major factors, including the reciprocity of the relationships, the duration of a relationship, the followees' informativeness, and the overlap of the relationships, which affect the de- cision to unfollow. We conduct interview with 22 Korean respondents to supplement the quantitative results. They un- followed those who left many tweets within a short time, created tweets about uninteresting topics, or tweeted about the mundane details of their lives. To the best of our knowl- edge, this work is the first systematic study of the unfollow behavior in Twitter.},
year = {2011},
month = {Jan},
date-added = {2011-04-15 22:50:27 +0100},
date-modified = {2013-06-11 14:19:11 +0100},
URL = {http://an.kaist.ac.kr/~haewoon/papers/2011-chi-unfollow.pdf},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Kwak/Fragile%20Online%20Relationship%20A%20First.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p16223},
read = {Yes},
rating = {0}
}

@article{GayoAvello:2012p27695,
author = {D Gayo-Avello}, 
journal = {Arxiv},
title = {``I Wanted to Predict Elections with Twitter and all I got was this Lousy Paper'' A Balanced Survey on Election Prediction using Twitter Data},
abstract = {Predicting X from Twitter is a popular fad within the Twitter research subculture. It seems both appealing and relatively easy. Among such kind of studies, electoral prediction is maybe the most attractive, and at this moment there is a growing body of literature on such a topic.
This is not only an interesting research problem but, above all, it is extremely difficult. However, most of the authors seem to be more interested in claiming positive results than in providing sound and reproducible methods.
It is also especially worrisome that many recent papers seem to only acknowledge those studies supporting the idea of Twitter predicting elec- tions, instead of conducting a balanced literature review showing both sides of the matter.
After reading many of such papers I have decided to write such a survey myself. Hence, in this paper, every study relevant to the matter of electoral prediction using social media is commented.
From this review it can be concluded that the predictive power of Twitter regarding elections has been greatly exaggerated, and that hard research problems still lie ahead.},
year = {2012},
month = {Jan},
date-added = {2012-05-05 17:25:24 +0100},
date-modified = {2013-06-11 10:08:48 +0100},
URL = {http://arxiv.org/abs/1204.6441},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2012/Gayo-Avello/%E2%80%9CI%20Wanted%20to%20Predict%20Elections%20with%20Twitter%20and%20all%20I.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p27695},
rating = {0}
}

@article{Poschko:2011p31127,
author = {Jan P{\"o}schko}, 
journal = {arXiv preprint arXiv:1111.6553},
title = {Exploring twitter hashtags},
abstract = {Twitter messages often contain so-called hashtags to denote keywords related to them. Using a dataset of 29 million messages, I explore relations among these hashtags with respect to co-occurrences. Furthermore, I present an attempt to classify hashtags into five intuitive classes, using a machine-learning approach. The overall outcome is an interactive Web application to explore Twitter hash- tags.},
year = {2011},
date-added = {2013-05-28 09:50:41 +0100},
date-modified = {2013-06-11 12:59:43 +0100},
pmid = {12861692812677977357related:DZXdDXjpfbIJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/P%C3%B6schko/Exploring%20twitter%20hashtags.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p31127},
rating = {0}
}

@article{Choudhury:2010p6395,
author = {M Choudhury and Y Lin and H Sundaram and K Candan and A Kelliher}, 
journal = {Proceedings of the Fourth International AAAI Conference on Weblogs and Social Media},
title = {How does the data sampling strategy impact the discovery of information diffusion in social media},
abstract = {Platforms such as Twitter have provided researchers with ample opportunities to analytically study social phenomena. There are however, significant computational challenges due to the enormous rate of production of new information: researchers are therefore, often forced to analyze a judiciously selected ``sample'' of the data. Like other social media phenomena, information diffusion is a social process--it is affected by user context, and topic, in addition to the graph topology. This paper studies the impact of different attribute and topology based sampling strategies on the discovery of an important social media phenomena--information diffusion.
We examine several widely-adopted sampling methods that select nodes based on attribute (random, location, and activity) and topology (forest fire) as well as study the impact of attribute based seed selection on topology based sampling. Then we develop a series of metrics for evaluating the quality of the sample, based on user activity (e.g. volume, number of seeds), topological (e.g. reach, spread) and temporal characteristics (e.g. rate). We additionally correlate the diffusion volume metric with two external variables--search and news trends. Our experiments reveal that for small sample sizes (30%), a sample that incorporates both topology and user-context (e.g. location, activity) can improve on na ̈ıve methods by a significant margin of ∼15-20%.},
year = {2010},
month = {Jan},
date-added = {2011-01-13 15:33:45 +0000},
date-modified = {2013-06-11 15:37:47 +0100},
pmid = {17253791507581682139related:28EOLvbHce8J},
URL = {http://www.aaai.org/ocs/index.php/ICWSM/ICWSM10/paper/viewFile/1521/1832},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2010/Choudhury/How%20does%20the%20data%20sampling%20strategy%20impact%20the%20discovery%20of.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p6395},
rating = {0}
}

@article{Fabrega:2012p29841,
author = {J Fabrega and P Paredes}, 
journal = {arXiv preprint arXiv:1207.6839},
title = {Three Degrees of Distance on Twitter},
abstract = {Recent work has found that the propagation of be- haviors and sentiments through networks extends in ranges up to 2 to 4 degrees of distance. The regularity with which the same observation is found in dissimilar phenomena has been associated with fric- tion in the propagation process and the instability of link structure that emerges in the dynamic of social networks. We study a contagious behavior, the prac- tice of retweeting, in a setting where neither of those restrictions is present and still found the same result.},
year = {2012},
date-added = {2012-10-26 12:49:47 +0100},
date-modified = {2013-06-11 15:10:09 +0100},
pmid = {related:gvsxxnk-G1IJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2012/Fabrega/Three%20Degrees%20of%20Distance%20on%20Twitter.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p29841},
rating = {0}
}

@article{Brown:2011p21131,
author = {P Brown and J Feng}, 
title = {Measuring User Influence on Twitter Using Modified K-Shell Decomposition},
abstract = {Social influence can be described as power - the ability of a person to influence the thoughts or actions of others. Identifying influential users on online social networks such as Twitter has been actively studied recently. In this paper, we investigate a modified k-shell decomposition algorithm for computing user influence on Twitter. The input to this algorithm is the connection graph between users as defined by the follower relationship. User influence is measured by the k-shell level, which is the output of the k-shell decomposition algorithm. Our first insight is to modify this k-shell decomposition to assign logarithmic k-shell values to users, producing a measure of users that is surprisingly well distributed in a bell curve. Our second insight is to identify and remove peering relationships from the network to further differentiate users. In this paper, we include findings from our study.},
year = {2011},
month = {Jan},
keywords = {AAAI Technical Report WS-11-02}, 
date-added = {2011-07-12 12:36:47 +0100},
date-modified = {2012-04-18 14:09:24 +0100},
URL = {http://www.aaai.org/ocs/index.php/ICWSM/ICWSM11/paper/download/3843/4385},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Brown/Measuring%20User%20Influence%20on%20Twitter%20Using%20Modified%20K-Shell%20Decomposition.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p21131},
rating = {0}
}

@article{Yu:2011p21398,
author = {L Yu and S Asur and B.A Huberman}, 
journal = {Arxiv preprint arXiv:1107.3522},
title = {What Trends in Chinese Social Media},
abstract = {There has been a tremendous rise in the growth of online so- cial networks all over the world in recent times. While some networks like Twitter and Facebook have been well docu- mented, the popular Chinese microblogging social network Sina Weibo has not been studied. In this work, we examine the key topics that trend on Sina Weibo and contrast them with our observations on Twitter. We find that there is a vast difference in the content shared in China, when com- pared to a global social network such as Twitter. In China, the trends are created almost entirely due to retweets of media content such as jokes, images and videos, whereas on Twitter, the trends tend to have more to do with current global events and news stories.},
year = {2011},
date-added = {2011-07-17 15:00:49 +0100},
date-modified = {2013-06-11 11:18:37 +0100},
pmid = {5239382445195111629related:zaxFEJMGtkgJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Yu/What%20Trends%20in%20Chinese%20Social%20Media.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p21398},
rating = {0}
}

@article{Biemann:2012p29899,
author = {F Bie{\ss}mann and JM Papaioannou and A Harth and ML Jugel and KR M{\"u}ller and M Braun}, 
title = {QUANTIFYING SPATIOTEMPORAL DYNAMICS OF TWITTER REPLIES TO NEWS FEEDS},
abstract = {Social network analysis can be used to assess the impact of in- formation published on the web. The spatiotemporal impact of a certain web source on a social network can be of partic- ular interest. We contribute a novel statistical learning algo- rithm for spatiotemporal impact analysis. To demonstrate our approach we analyze Twitter replies to individual news arti- cle along with their geospatial and temporal information. We then compute the multivariate spatiotemporal response pat- tern of all Twitter replies to information published on a given web source. This quantitative result can be interpreted with respect to a) how much impact a certain web source has on the Twitter-sphere b) where and c) when it reaches it maxi- mal impact. We also show that the proposed approach pre- dicts the dynamics of the social network activity better than classical trend detection methods.},
year = {2012},
date-added = {2012-11-03 08:49:56 +0000},
date-modified = {2012-11-03 08:51:10 +0000},
pmid = {related:LYZ_ceRIpuMJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2012/Bie%C3%9Fmann/QUANTIFYING%20SPATIOTEMPORAL%20DYNAMICS%20OF%20TWITTER%20REPLIES%20TO%20NEWS%20FEEDS.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p29899},
rating = {0}
}

@article{Szomszor:2011p24270,
author = {Martin Szomszor and Patty Kostkova and Connie St Louis}, 
journal = {Web Intelligence and Intelligent Agent Technology (WI-IAT), 2011 IEEE/WIC/ACM International Conference on},
title = {Twitter Informatics: Tracking and Understanding Public Reaction during the 2009 Swine Flu Pandemic},
abstract = {Much attention has been focused on Twitter because it serves as a central hub for the publishing, dissemination, and discovery of online media. This is true for both traditional news outlets and user generated content, both of which can vary widely in their journalistic and scientific quality. The recent Swine Flu pandemic of 2009 highlighted this aspect perfectly, global events that created a large online buzz, with some dubious medical facts leaking into public opinion. This paper presents an investigation into how online resources relating to Swine Flu were discussed on Twitter, with a focus on identifying and analyzing the popularity of trusted information sources (e.g. from quality news outlets and official health agencies). Our findings indicate that reputable sources are more popular than untrusted ones, but that information with poor scientific merit can still leak into to the network and potentially cause harm.},
pages = {320 -- 323},
volume = {1},
year = {2011},
date-added = {2011-10-27 08:54:22 +0100},
date-modified = {2012-04-18 14:09:29 +0100},
doi = { },
pmid = {6036779},
URL = {http://ieeexplore.ieee.org/search/srchabstract.jsp?tp=&arnumber=6036779&openedRefinements%253D*%2526sortType%253Ddesc_Publication+Year%2526filter%253DAND%2528NOT%25284283010803%2529%2529%2526matchBoolean%253Dtrue%2526rowsPerPage%253D50%2526searchField%253DSearch+All%2526queryText%253D%2528%2528DOI%253A10.1109%252Fwi-iat.2011.311%2529%2529},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Szomszor/Twitter%20Informatics%20Tracking%20and%20Understanding.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p24270},
rating = {0}
}

@article{GayoAvello:2010p18810,
author = {D Gayo-Avello and D.J Brenes}, 
title = {Overcoming Spammers in Twitter-A Tale of Five Algorithms},
abstract = {Micro-blogging services such as Twitter can develop into valuable sources of up-to-date information provided the spam problem is overcome. Thus, separating the most relevant users from the spammers is a highly pertinent question for which graph centrality methods can provide an answer. In this paper we examine the vulnerability of five different algorithms to linking malpractice in Twitter and propose a first step towards "desensitizing" them against such abusive behavior.},
year = {2010},
date-added = {2011-06-04 22:54:40 +0100},
date-modified = {2013-06-11 15:08:26 +0100},
pmid = {8817448006657691519related:f89Oxj7eXXoJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2010/Gayo-Avello/Overcoming%20Spammers%20in%20Twitter-A%20Tale%20of%20Five%20Algorithms.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p18810},
rating = {0}
}

@article{Ritter:2011p24223,
author = {A Ritter and S Clark and Mausam and O Etzioni}, 
title = {Named Entity Recognition in Tweets: An Experimental Study},
abstract = {Proceedings of EMNLP 2011},
pages = {1--11},
year = {2011},
month = {Jun},
date-added = {2011-10-18 21:51:05 +0100},
date-modified = {2012-04-18 14:10:57 +0100},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Ritter/Named%20Entity%20Recognition%20in%20Tweets%20An%20Experimental%20Study.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p24223},
rating = {0}
}

@article{Yang:2012p29793,
author = {X Yang and A Ghoting and Y Ruan and S Parthasarathy}, 
title = {Analysis of Streaming Data from Twitter Social Networks},
abstract = {The Twitter social network is a dynamic network that can generate high speed data streams. In Twitter, the users can subscribe to the contents shared by their friends. The contents are in the form of messages written by their au- thors. All the messages in the network form a data stream and carry the highly dynamic behaviors of the users in the Twitter network.
In this paper, we present our efforts to process the message stream of Twitter. We believe that in order to efficiently perform analysis on streaming data, we need an in-memory summary of the streaming data which can be used as input to mining algorithms. In this paper, we propose a novel sum- marization scheme to build such summary of the streaming data. We empirically demonstrate that our method can ef- fectively summarize message stream data from the Twitter social networks with limited memory consumption and high summarization quality.},
year = {2012},
date-added = {2012-10-26 12:49:45 +0100},
date-modified = {2012-11-03 15:05:18 +0000},
pmid = {related:PZYdEcwlsUEJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2012/Yang/Analysis%20of%20Streaming%20Data%20from%20Twitter%20Social%20Networks.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p29793},
rating = {0}
}

@article{Benevenuto:2010p6350,
author = {F Benevenuto and G Magno and T Rodrigues and V Almeida}, 
journal = {Proceedings of the 7th Annual Collaboration, Electronic messaging, Anti-Abuse and Spam Conference (CEAS)},
title = {Detecting spammers on twitter},
year = {2010},
date-added = {2011-01-05 00:34:00 +0000},
date-modified = {2012-04-18 14:11:00 +0100},
pmid = {4229583722446953353related:iZs5fPx_sjoJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2010/Benevenuto/Detecting%20spammers%20on%20twitter-1.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p6350},
read = {Yes},
rating = {0}
}

@inproceedings{sousa_characterization_2010,
author = {Daniel Sousa and Lu{\'\i}s Sarmento and Eduarda Mendes Rodrigues}, 
journal = {Proceedings},
title = {Characterization of the Twitter @replies Network: Are User Ties Social or Topical?},
abstract = {In recent years, social media services have become a global phenomenon on the Internet. The popularity of these ser- vices provides an opportunity to study the characteristics of online social networks and the communities that emerge in them. This paper presents an analysis of the users' in- teractions in the implicit network derived from tweet replies of a specific dataset obtained from a popular microblogging service, Twitter1. We analyze the influence of the topics of the tweet messages on the interaction among users, to determine if the social aspect prevails over the topic in the moment of interaction. Thus, the main goal of this paper is to investigate if people selectively choose whom to reply to based on the topic or, otherwise, if they reply to any- one about anything. We found that the social aspect pre- dominantly conditions users' interactions. For users with larger and denser ego-centric networks, we observed a slight tendency for separating their connections depending on the topics discussed.},
affiliation = {Toronto, Ontario, Canada},
pages = {63--70},
year = {2010},
date-added = {2013-04-13 21:02:22 +0100},
date-modified = {2013-06-11 12:22:16 +0100},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2010/Sousa/Characterization%20of%20the%20Twitter%20@replies%20Network%20Are%20User%20Ties%20Social.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p30607},
rating = {0}
}

@article{Suleimenov:2012p29795,
author = {A Suleimenov}, 
title = {TWITTER NEWS: HARNESSING TWITTER TO BUILD AN ARTICLE RECOMMENDATION SYSTEM},
abstract = {With more than 140 million active users and 340 million tweets a day (as of March 2012), Twitter presents a great source of recommendation knowledge for articles shared on the platform. In this work, we analyze 836 Twitter users from the technology and entrepreneurship domain with 78,508 links shared by them. We explore and evaluate different (existing and novel) techniques for a recommender system for articles including the following ones: vector-to-vector similarity where the user vector is constructed from the text of the tweets produced, topic-modeling based approach where we learn the topic distribution for each article, as well as the novel hybrid technique which is based on piecewise article vector representation, content-boosted collaborative filtering with pseudo user-ratings as well as the relatedness function which depends on relevance, novelty, connection size and transition smoothness between articles.},
year = {2012},
date-added = {2012-10-26 12:49:48 +0100},
date-modified = {2012-11-03 14:35:01 +0000},
pmid = {related:c3_wD2gh26YJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2012/Suleimenov/TWITTER%20NEWS%20HARNESSING%20TWITTER%20TO%20BUILD%20AN%20ARTICLE%20RECOMMENDATION%20SYSTEM.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p29795},
rating = {0}
}

@article{Campiolo:2013p30884,
author = {R Campiolo and L Santos and DM Batista and Gerosa M}, 
journal = {Proceedings of the 28th {\ldots}},
title = {Evaluating the utilization of Twitter messages as a source of security alerts},
abstract = {The fast spread of computer security alerts, like vulnerabil- ities notifications, applications updates and threats of at- tacks, is essential to the implementation of efficient reactive measures against security incidents. This paper presents an empirical study that evaluates the efficiency of using Twitter posts, related to computer security, as notifications of secu- rity alerts. The justification to this study is the fact that posts from microblogs have a very fast spread over the In- ternet. By using similarity analysis and clustering between Twitter posts and alerts from specialized sites, it was ver- ified that microblogs spread computer security alerts in a reliable way, reach a high level of dissemination and inform about security threats even before some specialized sites.},
year = {2013},
month = {Jan},
date-added = {2013-05-08 17:26:16 +0100},
date-modified = {2013-06-11 09:50:03 +0100},
URL = {http://dl.acm.org/citation.cfm?id=2480542},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2013/Campiolo/Evaluating%20the%20utilization%20of%20Twitter%20messages%20as%20a%20source%20of.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p30884},
rating = {0}
}

@article{Mao:2011p23591,
author = {H Mao and X Shuai and A Kapadia}, 
journal = {WPES'11},
title = {Loose Tweets: An Analysis of Privacy Leaks on Twitter},
abstract = {Twitter has become one of the most popular microblogging sites for people to broadcast (or ``tweet'') their thoughts to the world in 140 characters or less. Since these messages are available for public consumption, one may expect these tweets not to contain private or incriminating information. Nevertheless we observe a large number of users who un- wittingly post sensitive information about themselves and other people for whom there may be negative consequences. While some awareness exists of such privacy issues on social networks such as Twitter and Facebook, there has been no quantitative, scientific study addressing this problem.
In this paper we make three major contributions. First, we characterize the nature of privacy leaks on Twitter to gain an understanding of what types of private information peo- ple are revealing on it. We specifically analyze three types of leaks: divulging vacation plans, tweeting under the influ- ence of alcohol, and revealing medical conditions. Second, using this characterization we build automatic classifiers to detect incriminating tweets for these three topics in real time in order to demonstrate the real threat posed to users by, e.g., burglars and law enforcement. Third, we character- ize who leaks information and how. We study both self- incriminating primary leaks and secondary leaks that reveal sensitive information about others, as well as the prevalence of leaks in status updates and conversation tweets. We also conduct a cross-cultural study to investigate the prevalence of leaks in tweets originating from the United States, United Kingdom and Singapore. Finally, we discuss how our classi- fication system can be used as a defense mechanism to alert users of potential privacy leaks.},
year = {2011},
month = {Jan},
date-added = {2011-09-29 04:03:02 +0100},
date-modified = {2012-04-18 14:09:35 +0100},
URL = {http://www.cs.indiana.edu/~kapadia/papers/loosetweets-wpes11.pdf},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Mao/Loose%20Tweets%20An%20Analysis%20of%20Privacy%20Leaks%20on%20Twitter.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p23591},
rating = {0}
}

@article{Cheng:2010p3638,
author = {Z Cheng and J Caverlee and K Lee}, 
journal = {CIKM '10: Proceedings of the 19th ACM international conference on Information and knowledge management},
title = {You are where you tweet: a content-based approach to geo-locating twitter users},
abstract = {We propose and evaluate a probabilistic framework for es- timating a Twitter user's city-level location based purely on the content of the user's tweets, even in the absence of any other geospatial cues. By augmenting the massive human-powered sensing capabilities of Twitter and related microblogging services with content-derived location infor- mation, this framework can overcome the sparsity of geo- enabled features in these services and enable new location- based personalized information services, the targeting of re- gional advertisements, and so on. Three of the key features of the proposed approach are: (i) its reliance purely on tweet content, meaning no need for user IP information, private login information, or external knowledge bases; (ii) a clas- sification component for automatically identifying words in tweets with a strong local geo-scope; and (iii) a lattice-based neighborhood smoothing model for refining a user's location estimate. The system estimates k possible locations for each user in descending order of confidence. On average we find that the location estimates converge quickly (needing just 100s of tweets), placing 51% of Twitter users within 100 miles of their actual location.},
year = {2010},
month = {Oct},
keywords = {spatial data mining, geolization, text mining, twitter, location-based estimation}, 
date-added = {2010-11-26 16:48:59 +0000},
date-modified = {2012-04-18 14:09:26 +0100},
doi = {10.1145/1871437.1871535},
URL = {http://portal.acm.org/ft_gateway.cfm?id=1871535&type=pdf&coll=DL&dl=GUIDE&CFID=116090877&CFTOKEN=46873869},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2010/Cheng/You%20are%20where%20you%20tweet.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p3638},
read = {Yes},
rating = {4}
}

@article{Yang:2010p32066,
author = {Jiang Yang and Scott Counts}, 
journal = {ICWSM},
title = {Predicting the Speed, Scale, and Range of Information Diffusion in Twitter.},
abstract = {We present results of network analyses of information diffusion on Twitter, via users' ongoing social interactions as denoted by ``@username'' mentions. Incorporating survival analysis, we constructed a novel model to capture the three major properties of information diffusion: speed, scale, and range. On the whole, we find that some properties of the tweets themselves predict greater information propagation but that properties of the users, the rate with which a user is mentioned historically in particular, are equal or stronger predictors. Implications for end users and system designers are discussed.},
pages = {355--358},
volume = {10},
year = {2010},
date-added = {2013-07-10 11:55:40 +0100},
date-modified = {2013-07-10 11:56:29 +0100},
pmid = {1688848571614394942related:PnqA9tP-bxcJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2010/Yang/Predicting%20the%20Speed%20Scale%20and%20Range%20of%20Information%20Diffusion%20in.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p32066},
rating = {0}
}

@article{Jansen:2009p405,
author = {B Jansen and M Zhang and K Sobel and A Chowdury}, 
journal = {Proceedings of the CHI 2009},
title = {Micro-blogging as online word of mouth branding},
abstract = {In this paper, we report research results investigating micro-blogging as a form of online word of mouth branding. We analyzed 149,472 micro-blog postings containing branding comments, sentiments, and opinions. We investigated the overall structure of these micro-blog postings, types of expressions, and sentiment fluctuations. Of the branding micro-blogs, nearly 20 percent contained some expressions of branding sentiments. Of these tweets with sentiments,},
year = {2009},
month = {Jan},
date-added = {2011-03-09 17:50:36 +0000},
date-modified = {2013-06-11 14:37:21 +0100},
pmid = {6834136775948073895related:p3vRXDC7114J},
URL = {http://portal.acm.org/citation.cfm?id=1520584&ampdl=GUIDE&ampcoll=GUIDE&ampCFID=46120180&ampCFTOKEN=76757245},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2009/Jansen/Micro-blogging%20as%20online%20word%20of%20mouth%20branding.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p14189},
rating = {0}
}

@article{gruzd_imagining_2011,
author = {Anatoliy Gruzd and Barry Wellman and Yuri Takhteyev}, 
journal = {American Behavioral Scientist},
title = {Imagining Twitter as an Imagined Community},
abstract = {The notion of ``community'' has often been caught between concrete social relationships and imagined sets of people perceived to be similar. The rise of the Internet has refocused our attention on this ongoing tension. The Internet has enabled people who know each other to use social media, from email to Facebook, to interact without meeting physically. Into this mix came Twitter, an asymmetric micro-blogging service: if you follow me, I do not have to follow you. This means that connections on Twitter depend less on in-person contact, as many users have more followers than they know. Yet, there is a possibility that Twitter can form the basis of interlinked personal communities -- and even of a sense of community. Our analysis of one person's Twitter network shows that it is the basis for a real community, even though Twitter was not designed to support the development of online communities. Studying Twitter is useful for understanding how people use new communication technologies to form new social connections and maintain existing ones.},
number = {10},
pages = {1294--1318},
volume = {55},
year = {2011},
date-added = {2013-04-13 21:02:22 +0100},
date-modified = {2013-06-11 14:52:29 +0100},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Gruzd/Imagining%20Twitter%20as%20an%20Imagined%20Community.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p30623},
rating = {0}
}

@article{Gupta:2011p21140,
author = {S Gupta and B Slawski and D Xin and W Yao}, 
title = {The Twitter Rumor Network: Subject and Sentiment Cascades in a Massive Online Social Network},
abstract = {Tendencies of individuals to behave like those around them leads to cascading phenomenon, in which an idea or behavior spreads quickly throughout a social network, being adopted by nearly all individuals in an area. We crawl the Twitter social graph and monitor users' posts, or 'tweets,' for several weeks, monitoring the spread of keywords, or 'hashtags,' along the graph structure. We simulate cascades on the Twitter graph using previous models and compare the results to the real cascade data. Additionally, we perform sentiment analysis on the tweets, determining whether a user has a positive or negative position on a hashtag. Finally, we isolate clusters in the network, examining the variance in sentiment within a cluster, observing the distribution of group sentiment divisions.},
year = {2011},
date-added = {2011-07-12 12:55:00 +0100},
date-modified = {2012-04-18 14:10:29 +0100},
pmid = {related:8e4Rp5guv1wJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Gupta/The%20Twitter%20Rumor%20Network%20Subject%20and%20Sentiment%20Cascades%20in%20a.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p21140},
rating = {0}
}

@article{Achrekar:2011p24413,
author = {H Achrekar and A Gandhe and R Lazarus and SH Yu and B Liu}, 
journal = {cs.uml.edu},
title = {TWITTER IMPROVES SEASONAL INFLUENZA PREDICTION},
abstract = {Seasonal influenza epidemics causes severe illnesses and 250,000 to 500,000 deaths worldwide each year. Other pandemics like the 1918 ``Spanish Flu'' may change into a devastating one. Reducing the impact of these threats is of paramount importance for health authorities, and studies have shown that effective inter- ventions can be taken to contain the epidemics, if early detection can be made. In this paper, we introduce the Social Network Enabled Flu Trends (SNEFT), a continuous data collection framework which monitors flu related tweets and track the emergence and spread of an influenza. We show that text mining significantly enhances the correlation between the Twitter and the Influenza like Illness (ILI) rates provided by Centers for Disease Control and Prevention (CDC). For accurate prediction, we implemented an auto-regression with exogenous input (ARX) model which uses current Twitter data, and CDC ILI rates from previous weeks to predict current influenza statistics. Our results show that, while previous ILI data from CDC offer a true (but delayed) assessment of a flu epidemic, Twitter data provides a real-time assessment of the current epidemic condition and can be used to compensate for the lack of current ILI data. We observe that the Twitter data is highly correlated with the ILI rates across different regions within USA and can be used to effectively improve the accuracy of our prediction. Our age-based flu prediction analysis indicates that for most of the regions, Twitter data best fit the age groups of 5-24 and 25-49 years, correlating well with the fact that these are likely, the most active user age groups on Twitter. Therefore, Twitter data can act as supplementary indicator to gauge influenza within a population and helps discovering flu trends ahead of CDC.},
year = {2011},
date-added = {2011-10-31 23:06:39 +0000},
date-modified = {2012-04-18 14:09:55 +0100},
URL = {http://www.cs.uml.edu/~hachreka/SNEFT/images/healthinf_2012.pdf},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Achrekar/TWITTER%20IMPROVES%20SEASONAL%20INFLUENZA%20PREDICTION.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p24413},
rating = {0}
}

@article{Thoring:2011p16168,
author = {A Thoring}, 
journal = {Publishing Research Quarterly},
title = {Corporate Tweeting: Analysing the Use of Twitter as a Marketing Tool by UK Trade Publishers},
abstract = {The rapid growth and popularity of the microblogging service Twitter has been one of the most recent phenomena of the Internet, which opens up opportunities for businesses in general and publishers in particular to do marketing in a dialogue- and consumer-oriented way. This survey analysed UK trade publishers' use of Twitter with the specific objective of finding out what influence a publisher's size has on its Twitter adoption, patterns of use and the content of its Tweets. Overall, the results suggest that a publisher's size primarily affects its general Twitter use, while being less influential regarding its patterns of use and the tweeted content.},
year = {2011},
date-added = {2011-04-14 18:51:15 +0100},
date-modified = {2012-04-18 14:11:00 +0100},
doi = {10.1007/s12109-011-9214-7},
URL = {http://www.springerlink.com/index/8285H7G568117334.pdf},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Thoring/Corporate%20Tweeting%20Analysing%20the%20Use.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p16168},
rating = {0}
}

@article{Gloor:2009p2074,
author = {P Gloor and J Krauss and S Nann and K Fischbach and D Schoder}, 
journal = {proceddins of 2009 International Conference on Computational Science and Engineering},
title = {Web science 2.0: Identifying trends through semantic social network analysis},
abstract = {We introduce a novel set of social network analysis based algorithms for mining the Web, blogs, and online forums to identify trends and find the people launching these new trends. These algorithms have been implemented in Condor, a software system for predictive search and analysis of the Web and especially social networks. Algorithms include the temporal computation of network centrality measures, the visualization of social networks as Cybermaps, a semantic process of mining and analyzing large amounts of text based on social network analysis, and sentiment analysis and information filtering methods. The temporal calculation of betweenness of concepts permits to extract and predict long-term trends on the popularity of relevant concepts such as brands, movies, and politicians. We illustrate our approach by qualitatively comparing Web buzz and our Web betweenness for the 2008 US presidential elections, as well as correlating the Web buzz index with share prices. et al. Web science 2.0: Identifying trends through semantic social network analysis. proceddins of 2009 International Conference on Computational Science and Engineering (2009)},
year = {2009},
month = {Jan},
date-added = {2010-11-07 15:39:48 +0000},
date-modified = {2012-04-18 14:10:06 +0100},
doi = {10.1109/CSE.2009.186},
pmid = {2223550994020127534related:LlOJItmj2x4J},
URL = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=5284145},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2009/Gloor/Web%20science%202.0%20Identifying%20trends%20through%20semantic%20social%20network%20analysis.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p2074},
read = {Yes},
rating = {0}
}

@article{Quercia:2011p24218,
author = {D Quercia and J Ellis and L Capra and J Crowcroft}, 
journal = {cl.cam.ac.uk},
title = {In the Mood for Being Influential on Twitter},
abstract = {Researchers have widely studied how information diffuses in Twitter and have often done so by modeling the social-networking site as a communication graph in which tweets spread depending on its nodes' graph properties (e.g., degree, centrality). The resulting models are tractable but make a crucial assumption: that the human being behind an account is a node and that, consequently, human expression in Twitter can be modeled as a set of abstract nodes communicating with each other. We set out to test whether Twitter users can be reduced to look-alike nodes or, instead, whether they show individual differences that impact their popularity and influence. One aspect that may differentiate users is their character and personality. The problem is that personality is difficult to observe and quantify on Twitter. It has been shown, however, that personality is linked to what is unobtrusively observable in tweets: the use of language. We thus carry out a study of tweets - more specifically, we compare five different categories of user (one of which is influencer) and look at their language use. We find that popular and influential users linguistically structure their tweets in specific ways, and that influential users tend to be individuals who express negative sentiment in part of their tweets. These findings suggest that the popularity and influence of a Twitter account cannot be simply traced back to the graph properties of the network within which it is embedded, but also depends on the personality and emotions of the human being behind it.},
year = {2011},
date-added = {2011-10-13 02:52:41 +0100},
date-modified = {2012-04-18 14:10:05 +0100},
URL = {http://www.cl.cam.ac.uk/~dq209/publications/quercia11mood.pdf},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Quercia/In%20the%20Mood%20for%20Being%20Influential%20on%20Twitter.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p24218},
rating = {0}
}

@article{DanescuNiculescuMizil:2011p14485,
author = {C Danescu-Niculescu-Mizil and M Gamon and S Dumais}, 
journal = {Proceedings of WWW},
title = {Mark My Words! Linguistic Style Accommodation in Social Media},
abstract = {The psycholinguistic theory of communication accommodation accounts for the general observation that participants in conversations tend to converge to one another's communicative behavior: they coordinate in a variety of dimensions including choice of words, syntax, utterance length, pitch and gestures. In its almost forty years of existence, this theory has been empirically supported exclusively through small-scale or controlled laboratory studies. Here we address this phenomenon in the context of Twitter conversations. Undoubtedly, this setting is unlike any other in which accommodation was observed and, thus, challenging to the theory. Its novelty comes not only from its size, but also from the non real-time nature of conversations, from the 140 character length restriction, from the wide variety of social relation types, and from a design that was initially not geared towards conversation at all. Given such constraints, it is not clear a priori whether accommodation is robust enough to occur given the constraints of this new environment. To investigate this, we develop a probabilistic framework that can model accommodation and measure its effects. We apply it to a large Twitter conversational dataset specifically developed for this task. This is the first time the hypothesis of linguistic style accommodation has been examined (and verified) in a large scale, real world setting.
Furthermore, when investigating concepts such as stylistic influence and symmetry of accommodation, we discover a complexity of the phenomenon which was never observed before. We also explore the potential relation between stylistic influence and network features commonly associated with social status.},
annote = {The data citations in this paper are wrongly cited! },
pages = {141--150},
year = {2011},
date-added = {2011-03-14 20:51:41 +0000},
date-modified = {2012-04-18 14:09:49 +0100},
pmid = {related:f_ENXI69eUEJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Danescu-Niculescu-Mizil/Mark%20My%20Words!%20Linguistic%20Style%20Accommodation%20in%20Social%20Media.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p14485},
read = {Yes},
rating = {5}
}

@inproceedings{honeycutt_beyond_2009,
author = {Courtenay Honeycutt and Susan C Herring}, 
journal = {Proceedings},
title = {Beyond Microblogging: Conversation and Collaboration via Twitter},
abstract = {The microblogging service Twitter is in the process
of being appropriated for conversational interaction
and is starting to be used for collaboration, as well. In
order to determine how well Twitter supports user-touser exchanges, what people are using Twitterfor, and
what usage or design modifications would make it
(more) usable as a tool for collaboration, this study
analyzes a corpus of naturally-occurring public Twitter messages (tweets), focusing on the functions and
uses of the @ sign and the coherence of exchanges.
The findings reveal a surprising degree of conversationality, facilitated especially by the use of @ as a
marker of addressivity, and shed light on the limitations of Twitter's current design for collaborative use.},
affiliation = {Los Alamitos, CA},
year = {2009},
date-added = {2013-04-13 21:02:21 +0100},
date-modified = {2013-06-11 14:49:00 +0100},
URL = {Preprint:%20http://ella.slis.indiana.edu/~herring/honeycutt.herring.2009.pdf},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2009/Honeycutt/Beyond%20Microblogging%20Conversation%20and%20Collaboration%20via%20Twitter.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p30614},
read = {Yes},
rating = {0}
}

@article{Zhao:2011p27418,
author = {X Zhao and J Jiang}, 
journal = {Technical Paper Series, Singapore Management University School of Information Systems},
title = {An empirical comparison of topics in Twitter and traditional media},
abstract = {Twitter as a new form of social media can potentially contain much useful information, but content analysis on Twitter has not been well studied. In particular, it is not clear whether as an information source Twitter can be simply regarded as a faster news feed that covers mostly the same information as traditional news media. In This paper we empirically compare the content of Twitter with a traditional news medium, New York Times, using unsupervised topic modeling. We use a Twitter-LDA model to discover topics from a representative sample of the entire Twitter. We then use text mining techniques to compare these Twitter topics with topics from New York Times, taking into consideration of topic categories and types. We find that although Twitter and New York Times cover similar categories and types of topics, the distributions of topic categories and types are quite different. Furthermore, there are Twitter-specific topics and NYT-specific topics, and they tend to belong to certain topic categories and types. We also study the relation between the proportions of opinionated tweets and retweets and topic categories and types, and find some interesting dependence. To the best of our knowledge, ours is the first comprehensive empirical comparison between Twitter and traditional news media.},
year = {2011},
date-added = {2012-02-24 21:42:19 +0000},
date-modified = {2012-04-18 14:09:39 +0100},
pmid = {8792022080293968280related:mBlQ-X-JA3oJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Zhao/An%20empirical%20comparison%20of%20topics.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p27418},
rating = {0}
}

@article{Chang:2012p29843,
author = {J Chang and H Kim}, 
title = {Twitter Search Methods using Retweet Information},
abstract = {Recently, as social network services such as Twitter and FaceBook are becoming more popular, a large number of researches have been carried out with various approaches. However, since social network services have been launched recently, its related search methods are still at an early stage of practical service. Thus, most of current web search sites provide a simple search service for social network service posting articles in the order of their upload time. In this paper, we present a novel way of searching informative posting data in Twitter. The proposed method uses both the frequency of retweets and the number of users' followers as major factors of ranking function in order to evaluate the quality of postings.},
pages = {67--71},
year = {2012},
date-added = {2012-10-26 12:49:47 +0100},
date-modified = {2013-06-11 15:40:57 +0100},
pmid = {related:1Ye0SjVuqUMJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2012/Chang/Twitter%20Search%20Methods%20using%20Retweet%20Information.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p29843},
rating = {0}
}

@article{MacKinnon:2007p20529,
author = {R MacKinnon}, 
journal = {World Journalism Education Congress in Singapore},
title = {Blogs and China Correspondence: How foreign correspondents covering China use blogs},
abstract = {Recent research shows that journalists read blogs much more than the general public. This paper hypothesizes that journalists with specialized beats use blogs more heavily than general reporters. A survey of foreign correspondents who cover China indicates that blogs are especially useful to this group. This paper analyzes why blogs are so useful to China correspondents and calls for more comparative research so that the relationship between blogs and international news can be better understood.},
year = {2007},
date-added = {2011-06-25 13:02:08 +0100},
date-modified = {2012-04-18 14:09:19 +0100},
pmid = {13934784488249373319related:hzK6k6lMYsEJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2007/MacKinnon/Blogs%20and%20China%20Correspondence%20How%20foreign%20correspondents%20covering%20China%20use.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p20529},
rating = {0}
}

@article{Golder:2011p24068,
author = {S. A Golder and M. W Macy}, 
journal = {Science},
title = {Diurnal and Seasonal Mood Vary with Work, Sleep, and Daylength Across Diverse Cultures},
abstract = {We identified individual-level diurnal and seasonal mood rhythms in cultures across the globe, using data from millions of public Twitter messages. We found that individuals awaken in a good mood that deteriorates as the day progresses---which is consistent with the effects of sleep and circadian rhythm---and that seasonal change in baseline positive affect varies with change in daylength. People are happier on weekends, but the morning peak in positive affect is delayed by 2 hours, which suggests that people awaken later on weekends.},
number = {6051},
pages = {1878--1881},
volume = {333},
year = {2011},
month = {Sep},
date-added = {2011-10-01 14:32:17 +0100},
date-modified = {2012-04-18 14:10:57 +0100},
doi = {10.1126/science.1202775},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Golder/Diurnal%20and%20Seasonal%20Mood%20Vary.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p24068},
rating = {0}
}

@article{Bamman:2012p29786,
author = {D Bamman and J Eisenstein and T Schnoebelen}, 
journal = {arXiv preprint arXiv:1210.4567},
title = {Gender in Twitter: Styles, stances, and social networks},
abstract = {We present a study of the relationship between gender, linguistic style, and social networks, us- ing a novel corpus of 14,000 users of Twitter. Prior quantitative work on gender often treats this social variable as a binary; we argue for a more nuanced approach. By clustering Twitter feeds, we find a range of styles and interests that reflects the multifaceted interaction between gender and language. Some styles mirror the aggregated language-gender statistics, while others contra- dict them. Next, we investigate individuals whose language better matches the other gender. We find that such individuals have social networks that include significantly more individuals from the other gender, and that in general, social network homophily is correlated with the use of same-gender language markers. Pairing computational methods and social theory thus offers a new perspective on how gender emerges as individuals position themselves relative to audiences, topics, and mainstream gender norms.},
year = {2012},
month = {Dec},
date-added = {2012-10-26 12:45:48 +0100},
date-modified = {2012-11-03 06:16:35 +0000},
pmid = {17510996514470536988},
URL = {http://arxiv.org/abs/1210.4567},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2012/Bamman/Gender%20in%20Twitter%20Styles%20stances%20and%20social%20networks.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p29786},
rating = {0}
}

@article{Kwak:2010p8155,
author = {H Kwak and C Lee and H Park and S Moon}, 
journal = {WWW 2010},
title = {What is Twitter, a social network or a news media?},
abstract = {Twitter, a microblogging service less than three years old, com- mands more than 41 million users as of July 2009 and is growing fast. Twitter users tweet about any topic within the 140-character limit and follow others to receive their tweets. The goal of this paper is to study the topological characteristics of Twitter and its power as a new medium of information sharing.
We have crawled the entire Twitter site and obtained 41.7 million user profiles, 1.47 billion social relations, 4, 262 trending topics, and 106 million tweets. In its follower-following topology analysis we have found a non-power-law follower distribution, a short effective diameter, and low reciprocity, which all mark a deviation from known characteristics of human social networks [28]. In order to identify influentials on Twitter, we have ranked users by the number of followers and by PageRank and found two rankings to be similar. Ranking by retweets differs from the previous two rankings, indicating a gap in influence inferred from the number of followers and that from the popularity of one's tweets. We have analyzed the tweets of top trending topics and reported on their temporal behavior and user participation. We have classified the trending topics based on the active period and the tweets and show that the majority (over 85%) of topics are headline news or persistent news in nature. A closer look at retweets reveals that any retweeted tweet is to reach an average of 1, 000 users no matter what the number of followers is of the original tweet. Once retweeted, a tweet gets retweeted almost instantly on next hops, signifying fast diffusion of information after the 1st retweet.
To the best of our knowledge this work is the first quantitative study on the entire Twittersphere and information diffusion on it.},
year = {2010},
month = {Jan},
date-added = {2011-01-17 15:28:58 +0000},
date-modified = {2013-06-11 14:19:18 +0100},
pmid = {9291640701307833453related:bcwDFv2J8oAJ},
URL = {http://portal.acm.org/citation.cfm?id=1772690.1772751},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2010/Kwak/What%20is%20Twitter%20a%20social.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p8155},
read = {Yes},
rating = {0}
}

@article{Giller:2009p3350,
author = {GL Giller}, 
title = {Maximum Likelihood Estimation of a Poissonian Count Rate Function for the Followers of a Twitter Account Making Directional Forecasts of the Stock Market},
abstract = {We derive expressions of use in the maximum likelihood estimation of a parameterized growth rate where the quantity growing is a Poissonian count rate parame- terized in such a manner as to make it suitable to measure the number of Twitter accounts following an account that makes directional forecasts of the stock market. We use these expressions to estimate the model for data collected for a forecasting system publicised during the Spring of 2009. We find a positive correlation between success and an increase in the number of followers, and use the maximum likelihood ratio test to reject the null hypothesis (of no correlation) with a confidence of better than 95%.},
year = {2009},
date-added = {2010-11-20 12:20:51 +0000},
date-modified = {2012-04-18 14:09:46 +0100},
pmid = {related:gyXWLjcfxxMJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2009/Giller/Maximum%20Likelihood%20Estimation%20of%20a.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p3350},
read = {Yes},
rating = {3}
}

@article{Yerva:2012p26830,
author = {S Yerva and Z Miklos and K Aberer}, 
journal = {tmrfindia.org
},
title = {Entity-based Classification of Twitter Messages},
abstract = {Twitter is a popular micro-blogging service on the Web, where people can enter short messages, which then become visible to some other users of the service. While the topics of these messages varies, there are a lot of messages where the users express their opinions about some companies or their products. These messages are a rich source of information for companies for sentiment analysis or opinion mining. There is however a great obstacle for analyzing the messages directly: as the company names are often ambiguous (e.g. apple, the fruit vs. Apple Inc.), one needs first to identify, which messages are related to the company. In this paper we address this question. We present various techniques for classifying tweet messages containing a given keyword, whether they are related to a particular company with that name or not. We first present simple techniques, which make use of company profiles, which we created semi-automatically from external Web sources. Our advanced techniques take ambiguity estimations into account and also automatically extend the company profiles from the twitter stream itself. We demonstrate the effectiveness of our methods through an extensive set of experiments. Moreover, we extensively analyze the sources of errors in the classification. The analysis not only brings further improvement, but also enables to use the human input more efficiently.},
year = {2012},
date-added = {2012-02-07 12:43:21 +0000},
date-modified = {2012-04-18 14:10:56 +0100},
URL = {http://www.tmrfindia.org/ijcsa/v9i15.pdf},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2012/Yerva/Entity-based%20Classification%20of%20Twitter%20Messages.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p26830},
read = {Yes},
rating = {0}
}

@article{Bollen:2011p3,
author = {J Bollen and H Mao and X J Zeng}, 
journal = {Journal of Computational Science},
title = {Twitter mood predicts the stock market},
abstract = {Behavioral economics tells us that emotions can profoundly affect individual behavior and decision-making. Does this also apply to societies at large, i.e. can societies experience mood states that affect their collective decision making? By extension is the public mood correlated or even predictive of economic indicators? Here we investigate whether measurements of collective mood states derived from large-scale Twitter feeds are correlated to the value of the Dow Jones Industrial Average (DJIA) over time. We analyze the text content of daily Twitter feeds by two mood tracking tools, namely OpinionFinder that measures positive vs. negative mood and Google-Profile of Mood States (GPOMS) that measures mood in terms of 6 dimensions (Calm, Alert, Sure, Vital, Kind, and Happy). We cross-validate the resulting mood time series by comparing their ability to detect the public's response to the presidential election and Thanksgiving day in 2008. A Granger causality analysis and a Self-Organizing Fuzzy Neural Network are then used to investigate the hypothesis that public mood states, as measured by the OpinionFinder and GPOMS mood time series, are predictive of changes in DJIA closing values. Our results indicate that the accuracy of DJIA predictions can be significantly improved by the inclusion of specific public mood dimensions but not others. We find an accuracy of 87.6% in predicting the daily up and down changes in the closing values of the DJIA and a reduction of the Mean Average Percentage Error by more than 6%.},
year = {2011},
keywords = {sa}, 
date-added = {2010-10-26 19:50:29 +0100},
date-modified = {2013-07-31 11:50:04 +0100},
pmid = {4367143307342068974related:7jxZLbM1mzwJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Bollen/Twitter%20mood%20predicts%20the%20stock%20market.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p3},
read = {Yes},
rating = {3}
}

@article{Akcora:2010p14325,
author = {CG Akcora and MA Bayir and M Demirbas and H Ferhatosmanoglu}, 
journal = {1st Workshop on Social Media Analytics (SOMA '10)},
title = {Identifying breakpoints in public opinion},
abstract = {While polls are traditionally used for observing public opin- ion, they provide a point snapshot, not a continuum. We consider the problem of identifying breakpoints in public opinion, and propose using micro-blogging sites to capture trends in public opinion. We develop methods to detect changes in public opinion, and find events that cause these changes.
Our experiments show that the proposed methods are able to determine changes in public opinion and extract the ma- jor news about the events effectively. We also deploy an application where users can view the important news stories for a continuing event and find the related articles on web.},
year = {2010},
date-added = {2011-03-14 15:47:19 +0000},
date-modified = {2012-04-18 14:10:56 +0100},
pmid = {5547255889821507474related:kh8BV9fP-0wJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2010/Akcora/Identifying%20breakpoints%20in%20public%20opinion.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p14325},
read = {Yes},
rating = {0}
}

@article{Sankaranarayanan:2009p19894,
author = {J Sankaranarayanan and H Samet and BE Teitler and M Lieberman and J Sperling}, 
journal = {Proceedings of the {\ldots}},
title = {TwitterStand: news in tweets},
abstract = {Twitter is an electronic medium that allows a large user populace to communicate with each other simultaneously. Inherent to Twitter is an asymmetrical relationship between friends and followers that provides an interesting social network-like structure among the users of Twitter. Twitter messages, called tweets, are restricted to 140 characters and thus are usually very focused. We investigate the use of Twitter to build a news processing system, called TwitterStand, from Twitter tweets. The idea is to capture tweets that correspond to late breaking news. The result is analogous to a distributed news wire service. The difference is that the identities of the contributors/reporters are not known in advance and there may be many of them. Furthermore, tweets are not sent according to a schedule: they occur as news is happening, and tend to be noisy while usually arriving at a high throughput rate. Some of the issues addressed include removing the noise, determining tweet clusters of interest bearing in mind that the methods must be online, and determining the relevant locations associated with the tweets.},
year = {2009},
month = {Jan},
date-added = {2011-06-15 08:39:12 +0100},
date-modified = {2012-04-18 14:10:08 +0100},
pmid = {2372994619982301351related:p0j1wQiS7iAJ},
URL = {http://portal.acm.org/citation.cfm?id=1653781},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2009/Sankaranarayanan/TwitterStand%20news%20in%20tweets.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p19894},
rating = {0}
}

@inproceedings{yang_understanding_2010,
author = {Zi Yang and Jingyi Guo and Keke Cai and Jie Tang and Juanzi Li and Li Zhang and Zhong Su}, 
journal = {Proceedings},
title = {Understanding Retweeting Behaviors in Social Networks},
abstract = {Retweeting is an important action (behavior) on Twitter, in- dicating the behavior that users re-post microblogs of their friends. While much work has been conducted for mining textual content that users generate or analyzing the social network structure, few publications systematically study the underlying mechanism of the retweeting behaviors. In this paper, we perform an interesting analysis for the problem on Twitter. We have found that almost 25.5% of the tweets posted by users are actually retweeted from friends' blog spaces. Our investigation unveils that for the retweet behav- iors, some statistics still follows the power law distribution, while some others violate the state-of-the-art distribution for Web. Based on these important observations, we pro- pose a factor graph model to predict users' retweeting be- haviors. Experimental results on the Twitter data set show that our method can achieve a precision of 28.81% and recall of 37.33% for prediction of the retweet behaviors.},
affiliation = {Toronto, Ontario, Canada},
pages = {1633--1636},
year = {2010},
date-added = {2013-04-13 21:02:22 +0100},
date-modified = {2013-06-11 11:20:42 +0100},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2010/Yang/Understanding%20Retweeting%20Behaviors%20in%20Social%20Networks.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p30611},
rating = {0}
}

@article{Bhulai:2012p29838,
author = {S Bhulai and P Kampstra and L Kooiman and G Koole and M Deurloo and B Kok}, 
title = {Trend Visualization on Twitter: What's Hot and What's Not?},
abstract = {Twitter is a social networking service in which users can create short messages related to a wide variety of subjects. Certain subjects are highlighted by Twitter as the most popular subjects and are known as trending topics. In this paper, we study the visual representation of these trending topics to maximize the information toward the users in the most effective way. For this purpose, we present a new visual representation of the trending topics based on dynamic squarified treemaps. In order to use this visual representation, one needs to determine (preferably forecast) the speed at which tweets on a particular subject are posted and one needs to detect acceleration. Moreover, one needs efficient ways to relate topics to each other when necessary, so that clusters of related trending topics are formed to be more informative about a particular subject. We will outline the methodologies for determining the speed and acceleration, and for clustering. We show that the visualization using dynamic squarified treemaps has many benefits over other visualization techniques.},
pages = {43--48},
year = {2012},
date-added = {2012-10-26 12:49:46 +0100},
date-modified = {2013-06-11 10:10:51 +0100},
pmid = {related:-FNLNsNnepIJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2012/Bhulai/Trend%20Visualization%20on%20Twitter%20What's%20Hot%20and%20What's%20Not?.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p29838},
rating = {0}
}

@article{Hesse:2007p1723,
author = {H Hesse and K Mallela and C Volz}, 
journal = {groups.ischool.berkeley.edu},
title = {TwitterVis--Visualizing the Twitter Public Timeline},
year = {2007},
date-added = {2010-11-04 10:11:16 +0000},
date-modified = {2013-06-11 14:50:23 +0100},
pmid = {related:GfgPaUGIt-MJ},
URL = {http://groups.ischool.berkeley.edu/twitter/TwitterVis_Final_Writeup.pdf},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2007/Hesse/TwitterVis%E2%80%93Visualizing%20the%20Twitter%20Public%20Timeline.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p1723},
read = {Yes},
rating = {0}
}

@article{Kim:2013p30822,
author = {J Kim and B Ko and H Jeong and P Kim}, 
journal = {International Journal of Software Engineering and Its Applications
},
title = {A Method for Extracting Topics in News Twitter},
abstract = {Twitter that represents the social network makes it available to retweet the tweet that other users have written without restriction. Therefore, information can be conveniently delivered on a real-time basis. Thanks to such an advantage, studies that utilize twitter are recently being developed. This paper is intended to establish data base based on BBC News Twitter on a daily basis making a daily tweet as a token according to gap and moving to a phase of reprocessing that removes the stopwords. Each word that is created and retweeted after a phase of reprocessing is applied to calculate the total added retweet value, dividing them by the number of daily average retweet to derive topic weight value. This procedure is called `Topic Weight Measurement.' This way, the topics are extracted. After analyzing the pattern according to the date, topics that are extracted using proposed procedures are compared with frequency pattern that are provided by Google Trends. As a result, it was confirmed that topics provided by BBC News Twitter is similar with word searching pattern graph of Google Trends},
number = {2},
volume = {7},
year = {2013},
date-added = {2013-04-25 14:49:06 +0100},
date-modified = {2013-06-11 14:22:52 +0100},
URL = {http://www.sersc.org/journals/IJSEIA/vol7_no2_2013/1.pdf},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2013/Kim/A%20Method%20for%20Extracting%20Topics%20in%20News%20Twitter.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p30822},
rating = {0}
}

@article{Wigley:2011p24215,
author = {R Wigley}, 
journal = {Cultural Policy, Criticism and Management Research},
title = {Novel noise? A systems-theoretical approach to Twitter},
abstract = {This paper explores instances where communication using the medium of Twitter is shown to be in tension with communicative codes of the mass media and law, and asks whether the micro-blogging service can be described as a novel system of communication. Utilising Niklas Luhmann's systems-theoretical approach to sociological analysis to analyse specific cases, the paper assesses Twitter's potential stability as
a social system based on communication. Evidence regarding the basic conditions of system formation is sought in three cases where Twitter may be identified as a conduit for communication resulting in action or dissent. In asking whether Twitter fulfils the properties required for system formation, this paper suggests that Luhmann's systems theory provides a valuable framework for deeper analysis of social media tools.},
year = {2011},
date-added = {2011-10-06 15:15:38 +0100},
date-modified = {2012-04-18 14:09:33 +0100},
URL = {http://culturalpolicyjournal.org/current-issue/%25EF%25BB%25BFnovel-noise/},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Wigley/Novel%20noise?%20A%20systems-theoretical%20approach%20to%20Twitter.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p24215},
rating = {0}
}

@article{Sahito:2011p24304,
author = {F Sahito and A Latif and W Slany}, 
journal = {Emerging Technologies (ICET)},
title = {Weaving Twitter stream into Linked Data a proof of concept framework},
abstract = {Twitter is one of the most popular and well known micro blogging platforms. Its usage in all walks of life as a short message service makes it a highly valuable and trendy asset of today's web. But the knowledge and content delivered by Twitter explicitly or implicitly as short messages remains mostly unstructured and hidden for machine usage. In this paper, we have addressed the aforementioned problems by using the Semantic Web and Linked Data technologies. We explore an integrated approach by building a proof of concept framework, which uses Semantic Web technologies to triplify and link the unstructured content of tweets with Linked Data clouds as structured data. We are of the view that this proof of concept framework will be helpful in investigation of case studies like opinion mining, trend analysis in various settings and more importantly will bring the Social Web closer to the Semantic Web. In future we will extend our proposed framework in the domain of terrorism informatics.},
year = {2011},
date-added = {2011-10-27 08:58:10 +0100},
date-modified = {2012-04-18 14:09:34 +0100},
URL = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6048497},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Sahito/Weaving%20Twitter%20stream%20into%20Linked.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p24304},
rating = {0}
}

@article{Gabielkov:2012p30011,
author = {M Gabielkov and A Legout}, 
journal = {Proceedings of the 2012 ACM conference on {\ldots}},
title = {The complete picture of the Twitter social graph},
abstract = {Abstract In this work, we collected the entire Twitter social graph that consists of 537 million Twitter accounts connected by 23.95 billion links, and performed a preliminary analysis of the collected data. In order to collect the social graph, we implemented a distributed ... 
},
year = {2012},
month = {Jan},
date-added = {2012-12-20 08:31:52 +0000},
date-modified = {2012-12-20 08:33:23 +0000},
URL = {http://dl.acm.org/citation.cfm?id=2413260},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2012/Gabielkov/The%20complete%20picture%20of%20the%20Twitter%20social%20graph.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p30011},
rating = {0}
}

@article{Thongsuk:2011p25571,
author = {C Thongsuk and C Haruechaiyasak and S Saelee}, 
journal = {Proceeding of 2011 International Conference on Future Information Technology},
title = {Classifying Business Types on Twitter Based on User Influential Analysis},
abstract = {In this paper, we study the correlation between incoming link of users on Twitter, a micro-blogging website online social. Finding the influential user can apply to recommend users to follow their interest's businesses domain. To analyze and find characteristic of the influential users for applying to improve the performance of recommender system. We use user's Twitter posts from any solution into predefined business types. In this paper, we propose solution to applied user selection by comparing among three parameters: (1) the number of relevant posts (NumRP) (2) the number of incoming link from business follower (NumUFI) (3) the number of incoming link from every follower (NumTI). Each parameter is ranked and incremental organized into three groups of each parameter: (1) Top-100 (2) Top-200 and (3) Top-300. After that, we applied posts of selected users to build classification model. Comparison between among three user selection parameters and three user groups. From the experimental results, the performance of NumRP yielded the F-measure higher than NumUFI and NumTI respectively. In addition, users who organized into Top-100 user group of each user selection method are influential users.},
year = {2011},
month = {Jan},
date-added = {2012-01-01 19:48:05 +0000},
date-modified = {2012-04-18 14:09:51 +0100},
URL = {http://www.scientific.net/AMR.403-408.3719},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Thongsuk/Classifying%20Business%20Types%20on%20Twitter.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p25571},
rating = {0}
}

@article{Balabantaray:2012p28815,
author = {R Balabantaray and M Mohammad and N Sharma}, 
journal = {research.ijais.org
},
title = {Multi-Class Twitter Emotion Classification: A New Approach},
abstract = {Micro blogging today has become a very popular communication tool among Internet users. Millions of users share opinions on different aspects of life every day. Therefore micro blogging web-sites are rich sources of data for opinion mining and sentiment analysis. Because micro blogging has appeared relatively recently, there are a few research works that are devoted to this topic. In this paper, we are focusing on using Twitter, the most popular micro blogging platform, for the task of Emotion analysis. We will show how to automatically collect a corpus for Emotion analysis and opinion mining purposes and then perform linguistic analysis of the collected corpus and explain discovered phenomena. Using the corpus, we will build a Emotion classifier that will be able to determine the emotion class of the person writing.},
year = {2012},
date-added = {2012-09-30 21:14:42 +0100},
date-modified = {2013-07-10 09:24:12 +0100},
URL = {http://research.ijais.org/volume4/number1/ijais12-450651.pdf},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2012/Balabantaray/Multi-Class%20Twitter%20Emotion%20Classification%20A%20New%20Approach.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p28815},
rating = {0}
}

@article{Costajussa:2013p31939,
author = {Marta Costa-juss{\`a} and Rafael Banchs}, 
journal = {Language Resources and Evaluation},
title = {Automatic normalization of short texts by combining statistical and rule-based techniques},
pages = {1--15},
year = {2013},
date-added = {2013-07-10 09:57:12 +0100},
date-modified = {2013-07-10 09:57:17 +0100},
pmid = {related:H7rwaPVhTw4J},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2013/Costa-juss%C3%A0/Automatic%20normalization%20of%20short%20texts%20by%20combining%20statistical%20and%20rule-based.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p31939},
rating = {0}
}

@article{Zappavigna:2011p18968,
author = {M Zappavigna}, 
journal = {New Media {\&} Society},
title = {Ambient affiliation: A linguistic perspective on Twitter},
abstract = {This article explores how language is used to build community with the microblogging service, Twitter (www.twitter.com). Systemic Functional Linguistic (SFL), a theory of language use in its social context, is employed to analyse the structure and meaning of `tweets' (posts to Twitter) in a corpus of 45,000 tweets collected in the 24 hours after the announcement of Barak Obama's victory in the 2008 US presidential elections. This analysis examines the evaluative language used to affiliate in tweets. The article shows how a typographic convention, the hashtag, has extended its meaning potential to operate as a linguistic marker referencing the target of evaluation in a tweet (e.g. {\#}Obama). This both renders the language searchable and is used to upscale the call to affiliate with values expressed in the tweet. We are currently witnessing a cultural shift in electronic discourse from online conversation to such `searchable talk'.},
number = {19},
volume = {1},
year = {2011},
month = {Jan},
date-added = {2011-06-06 22:47:47 +0100},
date-modified = {2013-07-14 10:22:32 +0100},
doi = {10.1177/1461444810385097},
URL = {http://nms.sagepub.com/content/early/2011/05/26/1461444810385097.abstract},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2011/Zappavigna/Ambient%20affiliation%20A%20linguistic%20perspective%20on%20Twitter.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p18968},
read = {Yes},
rating = {0}
}

@article{Morozov:2009p16736,
author = {E Morozov}, 
journal = {Dissent},
title = {Iran: Downside to the" Twitter Revolution"},
number = {4},
pages = {10--14},
volume = {56},
year = {2009},
date-added = {2011-04-20 21:30:27 +0100},
date-modified = {2012-04-18 14:09:25 +0100},
doi = {10.1353/dss.0.0092},
pmid = {14368889456193781148related:nD1JrdSMaMcJ},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2009/Morozov/Iran%20Downside%20to%20the%22%20Twitter%20Revolution%22.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p16736},
rating = {0}
}

@article{Carvalho:2009p6363,
author = {Paula Carvalho and L Sarmento and M J SIlva and E Oliveira}, 
journal = {In Proceeding of the 1st international CIKM workshop on Topic-sentiment analysis for mass opinion (TSA '09). ACM, New York, NY, USA },
title = {Clues for detecting irony in user-generated contents: oh...!! it's so easy;-)},
abstract = {We investigate the accuracy of a set of surface patterns in identifying ironic sentences in comments submitted by users to an on-line newspaper. The initial focus is on identifying irony in sentences containing positive predicates since these sentences are more exposed to irony, making their true polarity harder to recognize. We show that it is possible to find ironic sentences with relatively high precision (from 45% to 85%) by exploring certain oral or gestural clues in user comments, such as emoticons, onomatopoeic expressions for laughter, heavy punctuation marks, quotation marks and positive interjections. We also demonstrate that clues based on deeper linguistic information are relatively inefficient in capturing irony in user-generated content, which points to the need for exploring additional types of oral clues.},
pages = {53--56},
year = {2009},
month = {Jan},
date-added = {2011-01-13 15:32:12 +0000},
date-modified = {2013-06-11 15:47:46 +0100},
doi = {10.1145/1651461.1651471},
pmid = {3975998442169591000related:2GQGdYSVLTcJ},
URL = {http://portal.acm.org/citation.cfm?id=1651461.1651471},
local-url = {file://localhost/Users/acepor/Dropbox/Papers/2009/Carvalho/Clues%20for%20detecting%20irony%20in%20user-generated%20contents%20oh...!!%20it's%20so.pdf},
uri = {papers://1BB16709-E0C1-4709-BEC5-06621A3EA216/Paper/p6363},
read = {Yes},
rating = {4}
}