DMI Summerschool Deepfakes Co-Hashtag Network

tweets-jsonl-to-co-hashtag-gexf.py

'''
Copyright 2021 Luca Hammer

Permission is hereby granted, free of charge, to any person obtaining a copy of
this software and associated documentation files (the "Software"), to deal in the 
Software without restriction, including without limitation the rights to use, copy, 
modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, 
and to permit persons to whom the Software is furnished to do so, subject to the 
following conditions:

The above copyright notice and this permission notice shall be included in all 
copies or substantial portions of the Software.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, 
INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A 
PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT 
HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF 
CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE 
OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
'''


import json_lines

def load_jsonl(file):
    tweets = []
    with open(file, 'rb') as f:
        for tweet in json_lines.reader(f, broken=True):
            reduced_tweet = {
                'created_at' : tweet['created_at'],
                'id' : tweet['id_str'],
                'username' : tweet['user']['screen_name'],
                'user_id' : tweet['user']['id_str'],
                'lang' : tweet['lang'],
                'hashtags' : list(map(lambda hashtag: hashtag['tag'].lower(), tweet['entities']['hashtags'])),
                'source' : tweet['source'],
                'urls' : list(map(lambda url: url['expanded_url'].lower(), tweet['entities']['urls']))
            }
                
            tweets.append(reduced_tweet)
    return (tweets)

# todo: add number of tweets
# todo: prevent duplicate edges
from itertools import combinations 
from collections import Counter
import lxml.etree as etree
import datetime

def create_gexf(tweets, filename):
    attr_qname = etree.QName("http://www.w3.org/2001/XMLSchema-instance", "schemaLocation")

    gexf = etree.Element('gexf',
                         {attr_qname : 'http://www.gexf.net/1.3draft  http://www.gexf.net/1.3draft/gexf.xsd'},
                         nsmap={None : 'http://graphml.graphdrawing.org/xmlns/graphml'},
                         version = '1.3')

    graph = etree.SubElement(gexf,
                             'graph',
                             defaultedgetype = 'undirected',
                             mode =  'dynamic',
                             timeformat='datetime')
    attributes = etree.SubElement(graph, 'attributes', {'class' : 'node', 'mode' : 'static'})
    etree.SubElement(attributes, 'attribute', {'id':'lang', 'title':'lang', 'type' : 'string'})
    etree.SubElement(attributes, 'attribute', {'id':'count', 'title':'count', 'type' : 'integer'})

    nodes = etree.SubElement(graph, 'nodes')
    edges = etree.SubElement(graph, 'edges')
    
    hashtag_counter = Counter()

    for tweet in reversed(tweets):
        
        hashtag_counter.update(tweet['hashtags'])
        
        for hashtag in tweet['hashtags']:
            
            node = etree.SubElement(nodes,
                                    'node',
                                    id = hashtag,
                                    Label = hashtag,
                                    start = datetime.datetime.strptime(tweet['created_at'],'%Y-%m-%dT%H:%M:%S.000Z').isoformat(timespec='seconds'), #Fri Jul 27 07:52:57 +0000 2018
                                    end = (datetime.datetime.strptime(tweet['created_at'],'%Y-%m-%dT%H:%M:%S.000Z') + datetime.timedelta(seconds=1)).isoformat(timespec='seconds')
                                   )
            attvalues = etree.SubElement(node,'attvalues')
            etree.SubElement(attvalues,
                             'attvalue',
                             {'for' : 'lang',
                             'value' : tweet['lang']
                             }
                            )
            etree.SubElement(attvalues,
                             'attvalue',
                             {'for' : 'count',
                             'value' : str(hashtag_counter[hashtag])
                             }
                            )
            for i, combination in enumerate(listset((combinations(tweet['hashtags'],2)))):
                etree.SubElement(edges,
                                 'edge',
                                 {'id' : f"{tweet['id']}_{i}",
                                  'source' : combination[0],
                                  'target' : combination[1],
                                  'start' : datetime.datetime.strptime(tweet['created_at'],'%Y-%m-%dT%H:%M:%S.000Z').isoformat(timespec='seconds'), #Fri Jul 27 07:52:57 +0000 2018
                                  'end' : (datetime.datetime.strptime(tweet['created_at'],'%Y-%m-%dT%H:%M:%S.000Z') + datetime.timedelta(seconds=1)).isoformat(timespec='seconds')
                                 }
                                )

    with open(filename, 'w', encoding='utf-8')as f:
        f.write(etree.tostring(gexf, encoding='utf8', method='xml').decode('utf-8'))
    print('Created gexf.')

tweets = load_jsonl('original_dataset/deepfakes_2017-2021.json')
create_gexf(tweets, '2021-07-07-co_hashtags-dynamic.gexf')