def __db_trustworthy_users(db_users, db_tweets, config):
"""
Generate a database of trustworthy users. We trust in the user if she
has a verified account or has more than X number of followers
:param db_users: database of user
:param config: dictionary with the configuration parameters of the heuristic
:return: database of trustworthy users
"""
trustworthy_users_db = DBManager('trustworthy_users')
if trustworthy_users_db.num_records_collection() == 0:
logging.info('The trustworthy_users collection is being created...')
for doc in db_users.find_all():
data = get_user(db_tweets, doc['screen_name'])
if data['verified'] or int(
data['followers_count']) > config['min_num_followers']:
if not trustworthy_users_db.find_record(
{'screen_name': data['screen_name']}):
trustworthy_users_db.save_record({
'screen_name':
doc['screen_name'],
'name':
data['name'],
'created_at':
data['created_at'],
'followers_count':
data['followers_count'],
'verified':
data['verified']
})
return trustworthy_users_db
class NetworkAnalyzer:
__dbm_tweets = None
__dbm_users = None
__dbm_networks = None
__network = None
__graph = None
__nodes = set()
__unknown_users = set()
__node_sizes = None
def __init__(self):
self.__dbm_tweets = DBManager('tweets')
self.__dbm_users = DBManager('users')
self.__dbm_networks = DBManager('networks')
self.__network = []
def __computer_ff_ratio(self, friends, followers):
if followers > 0 and friends > 0:
return friends / followers
else:
return 0
# Get interactions in of a given users
def get_in_interactions(self, user_screen_name):
# compute in interactions, meaning, interactions in which the user
# was mentioned, retweeted, quoted, replied
in_inter_query = {'interactions.' + user_screen_name: {'$exists': 1},
'screen_name': {'$ne': user_screen_name}}
n_users = self.__dbm_users.search(in_inter_query)
in_interactions_dict, in_rts, in_rps = {}, {}, {}
in_qts, in_mts = {}, {}
total_in_interactions = 0
total_in_retweets, total_in_replies = 0, 0
total_in_mentions, total_in_quotes = 0, 0
for n_user in n_users:
n_user_interactions = n_user['interactions']
for i_user, interactions in n_user_interactions.items():
if i_user == user_screen_name:
in_interactions_dict[n_user['screen_name']] = interactions['total']
total_in_interactions += interactions['total']
if 'retweets' in interactions.keys():
total_in_retweets += interactions['retweets']
in_rts[n_user['screen_name']] = interactions['retweets']
if 'replies' in interactions.keys():
total_in_replies += interactions['replies']
in_rps[n_user['screen_name']] = interactions['replies']
if 'mentions' in interactions.keys():
total_in_mentions += interactions['mentions']
in_mts[n_user['screen_name']] = interactions['mentions']
if 'quotes' in interactions.keys():
total_in_quotes += interactions['quotes']
in_qts[n_user['screen_name']] = interactions['quotes']
in_interactions_obj = {
'total': {
'count': total_in_interactions,
'details': in_interactions_dict
},
'replies': {
'count': total_in_replies,
'details': in_rps
},
'retweets': {
'count': total_in_retweets,
'details': in_rts
},
'mentions': {
'count': total_in_mentions,
'details': in_mts
},
'quotes': {
'count': total_in_quotes,
'details': in_qts
}
}
user_dict = {
'in_interactions': in_interactions_obj
}
return user_dict
# Get interactions out of a given users
def get_out_interactions(self, user_screen_name):
user = self.__dbm_users.search({'screen_name': user_screen_name})[0]
# compute out interactions, meaning, interactions originated by
# the user
user_interactions = user['interactions']
out_interactions_dict, out_rts = {}, {}
out_rps, out_qts, out_mts = {}, {}, {}
total_out_interactions, total_out_retweets = 0, 0
total_out_mentions, total_out_replies = 0, 0
total_out_quotes = 0
for recipient, interactions in user_interactions.items():
out_interactions_dict[recipient] = interactions['total']
total_out_interactions += interactions['total']
if 'retweets' in interactions:
total_out_retweets += interactions['retweets']
out_rts[recipient] = interactions['retweets']
if 'replies' in interactions:
total_out_replies += interactions['replies']
out_rps[recipient] = interactions['replies']
if 'mentions' in interactions:
total_out_mentions += interactions['mentions']
out_mts[recipient] = interactions['mentions']
if 'quotes' in interactions:
total_out_quotes += interactions['quotes']
out_qts[recipient] = interactions['quotes']
out_interactions_obj = {
'total': {
'count': total_out_interactions,
'details': out_interactions_dict
},
'replies': {
'count': total_out_replies,
'details': out_rps
},
'retweets': {
'count': total_out_retweets,
'details': out_rts
},
'mentions': {
'count': total_out_mentions,
'details': out_mts
},
'quotes': {
'count': total_out_quotes,
'details': out_qts
}
}
# compile all information in a dictionary
user_dict = {
'out_interactions': out_interactions_obj
}
return user_dict
def create_users_db(self, clear_collection=False):
logging.info('::. Network Analyzer: Creating database of users, it can take several minutes, please wait_')
if clear_collection:
self.__dbm_users.clear_collection()
users = self.__dbm_tweets.get_unique_users()
users_count = len(users)
logging.info('::. Network Analyzer: Extracted {0} unique users from the database...'.format(users_count))
progress = 1
for user in users:
db_user = {
'screen_name': user['screen_name'],
'friends': user['friends'],
'followers': user['followers'],
'ff_ratio': self.__computer_ff_ratio(user['friends'], user['followers']),
'interactions': user['interactions'],
'tweets': user['tweets_count'],
'original_tweets': user['original_count'],
'rts': user['retweets_count'],
'qts': user['quotes_count'],
'rps': user['replies_count'],
'verified': user['verified']
}
# Assign the party and movement to the party and movement that are more related to the user
# counting both Hashtags and Mentions by the user
user_parties = self.__dbm_tweets.get_party_user(user['screen_name'])
user_parties_count = len(user_parties) or 0
logging.debug('::. Network Analyzer: User {0} has {1} associated parties...'
.format(user['screen_name'],user_parties_count))
if user_parties_count > 0:
user_party = user_parties[0]
db_user.update({'most_interacted_party': user_party['partido']})
user_movements = self.__dbm_tweets.get_movement_user(user['screen_name'])
user_movements_count = len(user_movements) or 0
logging.debug('::. Network Analyzer: User {0} has {1} associated movements...'
.format(user['screen_name'], user_movements_count))
if user_movements_count > 0:
user_movement = user_movements[0]
db_user.update({'most_interacted_movement': user_movement['movimiento']})
else:
db_user.update({'most_interacted_movement': ''})
else:
db_user.update({'most_interacted_party': '', 'movement': ''})
# Assign the party and movement to the party and movement that are more related to the user
# counting both Hashtags and Mentions by the user
upp = UserPoliticalPreference()
user_party = upp.get_user_political_party(user['screen_name'])
user_movement = upp.get_user_political_movement(user['screen_name'])
db_user.update({'party': user_party, 'movement': user_movement})
filter_query = {'screen_name': user['screen_name']}
logging.debug('::. Network Analyzer: Updating/creating user {0} ({1}/{2})...'
.format(user['screen_name'], progress, users_count))
progress += 1
self.__dbm_users.update_record(filter_query, db_user, create_if_doesnt_exist=True)
def generate_network(self, subnet_query={}, depth=1, file_name='network', override_net=False):
net_query = subnet_query.copy()
net_query.update({'depth': depth})
ret_net = self.__dbm_networks.search(net_query)
# the net doesn't exist yet, let's create it
if ret_net.count() == 0 or override_net:
logging.info('Generating the network, it can take several minutes, please wait_')
users = self.__dbm_users.search(subnet_query)
# for each user generate his/her edges
for user in users:
if 'ff_ratio' in user.keys():
u_ff_ratio = user['ff_ratio']
else:
u_ff_ratio = self.__computer_ff_ratio(user['friends'], user['followers'])
pbb_score = user['bot_analysis']['pbb'] if 'bot_analysis' in user.keys() else ''
self.__nodes.add(tuple({'screen_name': user['screen_name'], 'party': user['party'],
'movement': user['movement'], 'ff_ratio': u_ff_ratio,
'pbb': pbb_score}.items()))
for interacted_user, interactions in user['interactions'].items():
iuser = self.__dbm_users.find_record({'screen_name': interacted_user})
if not iuser:
if depth > 1:
iuser_ffratio = self.__get_ffratio(interacted_user)
if not iuser_ffratio:
self.__unknown_users.add(interacted_user)
continue
else:
self.__unknown_users.add(interacted_user)
continue
else:
if 'ff_ratio' in iuser.keys():
i_ff_ratio = iuser['ff_ratio']
else:
i_ff_ratio = self.__computer_ff_ratio(iuser['friends'], iuser['followers'])
pbb_iuser_score = user['bot_analysis']['pbb'] if 'bot_analysis' in iuser.keys() else ''
self.__nodes.add(tuple({'screen_name': iuser['screen_name'], 'party': iuser['party'],
'movement': iuser['movement'], 'ff_ratio': i_ff_ratio,
'pbb': pbb_iuser_score}.items()))
edge = {
'nodeA': {'screen_name': user['screen_name'], 'ff_ratio': u_ff_ratio,
'party': user['party'], 'movement': user['movement'],
'pbb': pbb_score},
'nodeB': {'screen_name': interacted_user, 'ff_ratio': i_ff_ratio,
'party': iuser['party'], 'movement': iuser['movement'],
'pbb': pbb_iuser_score},
'weight': interactions['total']
}
self.__network.append(edge)
logging.info('Created a network of {0} nodes and {1} edges'.format(len(self.__nodes), len(self.__network)))
logging.info('Unknown users {0}'.format(len(self.__unknown_users)))
# save the net in a gefx file for posterior usage
f_name = self.save_network_in_gexf_format(file_name)
logging.info('Saved the network in the file {0}'.format(f_name))
db_net = {'file_name': str(f_name)}
db_net.update(net_query)
self.__dbm_networks.save_record(db_net)
else:
f_net = ret_net[0]
logging.info('The network was already generated, please find it at {0}'.format(f_net['file_name']))
def create_graph(self):
logging.info('Creating the graph, please wait_')
self.__graph = net.DiGraph()
ff_ratio = defaultdict(lambda: 0.0)
# create a directed graph from the edge data and populate a dictionary
# with the friends/followers ratio
for edge in self.__network:
user = edge['nodeA']['screen_name']
interacted_with = edge['nodeB']['screen_name']
num_interactions = edge['weight']
u_ff_ratio = edge['nodeA']['ff_ratio']
self.__graph.add_edge(user, interacted_with, weight=int(num_interactions))
ff_ratio[user] = float(u_ff_ratio)
# obtain central node
# degrees = net.degree(self.__graph)
# central_node, max_degree = sorted(degrees, key=itemgetter(1))[-1]
# center the graph around the central node
# ego_graph = net.DiGraph(net.ego_graph(self.__graph, central_node))
return
def get_graph_nodes(self):
return len(self.__nodes)
def get_graph_edges(self):
return len(self.__network)
def get_graph(self):
return self.__graph
def get_node_sizes(self):
return self.__node_sizes
def __get_ffratio(self, screen_name):
query = {
'$or': [
{'tweet_obj.user.screen_name': screen_name},
{'tweet_obj.retweeted_status.user.screen_name': screen_name},
{'tweet_obj.quoted_status.user.screen_name': screen_name}
]
}
tweet_obj = self.__dbm_tweets.find_record(query)
if tweet_obj:
tweet = tweet_obj['tweet_obj']
if 'retweeted_status' in tweet.keys():
return self.__computer_ff_ratio(tweet['retweeted_status']['user']['friends_count'],
tweet['retweeted_status']['user']['followers_count'])
elif 'quoted_status' in tweet.keys():
return self.__computer_ff_ratio(tweet['quoted_status']['user']['friends_count'],
tweet['quoted_status']['user']['followers_count'])
else:
return self.__computer_ff_ratio(tweet['user']['friends_count'],
tweet['user']['followers_count'])
else:
return None
def save_network_in_gexf_format(self, file_name):
today = datetime.strftime(datetime.now(), '%m/%d/%y')
f_name = pathlib.Path(__file__).parents[2].joinpath('sna', 'gefx', file_name+'.gexf')
with open(str(f_name), 'w', encoding='utf-8') as f:
f.write('<?xml version="1.0" encoding="UTF-8"?>\n')
f.write('<gexf xmlns="http://www.gexf.net/1.2draft" xmlns:viz="http://www.gexf.net/1.1draft/viz" '
'xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" '
'xsi:schemaLocation="http://www.gexf.net/1.2draft http://www.gexf.net/1.2draft/gexf.xsd" '
'version="1.2">\n')
f.write('<meta lastmodifieddate="{0}">\n'.format(today))
f.write('<creator>PoliticBots</creator>\n')
f.write('<description>{0}</description>\n'.format(file_name))
f.write('</meta>\n')
f.write('<graph mode="static" defaultedgetype="directed">\n')
# add data attributes
f.write('<attributes class="node">\n')
f.write('<attribute id="0" title="party" type="string"/>\n')
f.write('<attribute id="1" title="movement" type="string"/>\n')
f.write('<attribute id="2" title="ff_ratio" type="float"/>\n')
f.write('<attribute id="3" title="pbb" type="float"/>\n')
f.write('</attributes>\n')
# add nodes
f.write('<nodes>\n')
node_id = 0
list_nodes = []
for node_tup in self.__nodes:
node = dict(node_tup)
f.write('<node id="{0}" label="{1}">\n'.format(node_id, node['screen_name']))
f.write('<attvalues>\n')
f.write('<attvalue for="0" value="{0}"/>\n'.format(node['party']))
f.write('<attvalue for="1" value="{0}"/>\n'.format(node['movement']))
f.write('<attvalue for="2" value="{0}"/>\n'.format(node['ff_ratio']))
f.write('<attvalue for="3" value="{0}"/>\n'.format(node['pbb']))
f.write('</attvalues>\n')
#f.write('<viz:size value="{0}"/>\n'.format(node['ff_ratio']))
f.write('</node>\n')
node_id += 1
list_nodes.append(node['screen_name'])
f.write('</nodes>\n')
# add edges
f.write('<edges>\n')
edge_id = 0
for edge in list(self.__network):
id_vertexA = list_nodes.index(edge['nodeA']['screen_name'])
id_vertexB = list_nodes.index(edge['nodeB']['screen_name'])
weight = edge['weight']
f.write('<edge id="{0}" source="{1}" target="{2}" weight="{3}"/>\n'.format(edge_id, id_vertexA,
id_vertexB, weight))
edge_id += 1
f.write('</edges>\n')
f.write('</graph>\n')
f.write('</gexf>\n')
return f_name
class SentimentAnalysis:
config_file_name = pathlib.Path(__file__).parents[1].joinpath(
'config.json')
config = None
language = ''
method = ''
__db = None
def __init__(self, collection='tweets', language='spanish'):
self.config = get_config(self.config_file_name)
self.language = language
self.__dbm = DBManager(collection)
def __get_analyzed_tweet(self, analyzed_tweets, id_tweet_to_search):
for analyzed_tweet in analyzed_tweets:
if id_tweet_to_search == analyzed_tweet['id']:
return analyzed_tweet
return None
def update_sentiment_of_non_original_tweets(self,
query={},
update_sentiment=False):
if update_sentiment:
query.update({
'relevante': 1,
})
else:
query.update({'relevante': 1, 'sentimiento': {'$exists': 0}})
tweet_regs = self.__dbm.search(query)
rts_wo_tw = []
for tweet_reg in tweet_regs:
if 'retweeted_status' in tweet_reg['tweet_obj'].keys():
id_original_tweet = tweet_reg['tweet_obj']['retweeted_status'][
'id_str']
original_tweet_reg = self.__dbm.find_record(
{'tweet_obj.id_str': id_original_tweet})
if original_tweet_reg:
sentiment_ot = original_tweet_reg['sentimiento']
if sentiment_ot:
self.__dbm.update_record(
{
'tweet_obj.id_str':
tweet_reg['tweet_obj']['id_str']
}, {'sentimiento': sentiment_ot})
else:
raise Exception(
'Error, found an original tweet without sentiment')
else:
rts_wo_tw.append(tweet_reg['tweet_obj'])
elif tweet_reg['tweet_obj']['in_reply_to_status_id_str']:
rts_wo_tw.append(tweet_reg['tweet_obj'])
logging.info('Tweet not RT {0}'.format(
tweet_reg['tweet_obj']['id_str']))
self.__analyze_sentiment_of_rt_wo_tws(rts_wo_tw)
def __update_sentimient_rts(self, analyzed_tweets):
for analyzed_tweet in analyzed_tweets:
# search rts of the analyzed tweet
rts = self.__dbm.search(
{'tweet_obj.retweeted_status.id_str': analyzed_tweet['id']})
for rt in rts:
self.__dbm.update_record(
{'tweet_obj.id_str': rt['tweet_obj']['id_str']},
{'sentimiento': analyzed_tweet['sentimiento']})
def __analyze_sentiment_of_rt_wo_tws(self, tweets):
tot_tws = len(tweets)
batch_size = 5
tweets_to_analyze = []
for current_tw in range(tot_tws):
tweet_id = tweets[current_tw]['id_str']
if 'retweeted_status' in tweets[current_tw].keys():
tweet = tweets[current_tw]['retweeted_status']
else:
tweet = tweets[current_tw]
if 'full_text' in tweet.keys():
tweet_text = tweet['full_text']
else:
tweet_text = tweet['text']
if len(tweets_to_analyze) < batch_size and current_tw < tot_tws:
tweets_to_analyze.append({'id': tweet_id, 'text': tweet_text})
if len(tweets_to_analyze) < batch_size and current_tw < (
tot_tws - 1):
continue
sentiment_results = self.do_sentiment_analysis(tweets_to_analyze)
tweets_to_analyze = []
for sentiment_result in sentiment_results:
sentiment_info = sentiment_result['sentimiento']
tweet_id = sentiment_result['id']
tweet_text = sentiment_result['text']
self.__dbm.update_record({'tweet_obj.id_str': tweet_id},
{'sentimiento': sentiment_info})
logging.debug('Tweet text: {0}, Sentimiento: {1} ({2})'.format(
tweet_text.encode('utf-8'), sentiment_info['tono'],
sentiment_info['score']))
def analyze_sentiments(self, query={}, update_sentiment=False):
"""
:param query: dictionary of <key, value> terms to be used in querying the db
"""
if update_sentiment:
query.update({
'relevante': 1,
'tweet_obj.retweeted_status': {
'$exists': 0
}
})
else:
query.update({
'relevante': 1,
'tweet_obj.retweeted_status': {
'$exists': 0
},
'sentimiento': {
'$exists': 0
}
})
tweet_regs = self.__dbm.search(query)
analyzed_tweets = []
tot_reg = tweet_regs.count()
logging.info(
'Going to analyze the sentiment of {0} tweets, '
'it can take a lot of time, be patient...'.format(tot_reg))
batch_size = 100
total_batches = ceil(tot_reg / batch_size)
batch = 0
tweets_to_analyze = []
try:
for current_reg in range(tot_reg):
tweet_reg = tweet_regs[current_reg]
tweet = tweet_reg['tweet_obj']
if 'full_text' in tweet.keys():
tweet_text = tweet['full_text']
else:
tweet_text = tweet['text']
if len(tweets_to_analyze
) < batch_size and current_reg < tot_reg:
tweets_to_analyze.append({
'id': tweet['id_str'],
'text': tweet_text
})
if len(tweets_to_analyze) < batch_size:
continue
batch += 1
logging.info(
'Analyzing the sentiment of {0} tweets in batch {1}/{2} '
'out of {3} tweets...'.format(len(tweets_to_analyze),
batch, total_batches,
tot_reg))
sentiment_results = self.do_sentiment_analysis(
tweets_to_analyze)
logging.info(
'Finished analyzing the sentiment of {0} tweets in batch {1}/{2} '
'out of {3} tweets...'.format(len(tweets_to_analyze),
batch, total_batches,
tot_reg))
logging.info('Updating sentiment scores in database...')
tweets_to_analyze = []
for sentiment_result in sentiment_results:
sentiment_info = sentiment_result['sentimiento']
tweet_id = sentiment_result['id']
tweet_text = sentiment_result['text']
self.__dbm.update_record({'tweet_obj.id_str': tweet_id},
{'sentimiento': sentiment_info})
analyzed_tweets.append({
'id': tweet_id,
'texto': tweet_text,
'sentimiento': sentiment_info
})
logging.debug(
'Tweet text: {0}, Sentimiento: {1} ({2})'.format(
tweet_text.encode('utf-8'), sentiment_info['tono'],
sentiment_info['score']))
except Exception as e:
logging.error(e)
finally:
self.__update_sentimient_rts(analyzed_tweets)
return analyzed_tweets
def do_sentiment_analysis(self, tweets):
sa = SentimentAnalyzer(language='spanish')
tweet_texts = []
for tweet in tweets:
tweet_texts.append(tweet['text'] +
' -$%#$&- {0}'.format(tweet['id']))
sa.analyze_docs(tweet_texts)
results = sa.tagged_docs
logging.info(
'Finished the sentiment analysis, now {0} results are going to '
'be processed...'.format(len(results)))
ret = self.__process_results(results)
logging.info('Computed correctly the sentiment of {0} tweets'.format(
len(tweet_texts)))
return ret
def remote_sentiment_analysis(self, tweets):
accepted_codes = [200, 201, 202]
error_codes = [400, 401]
url_base = 'http://159.203.77.35:8080/api'
url_sentiment = url_base + '/analysis/sentiment-analysis/'
url_auth = url_base + '/auth/'
headers = {'Authorization': 'JWT ' + self.config['inhouse']['api_key']}
tweet_texts = []
for tweet in tweets:
tweet_texts.append(tweet['text'] +
' -$%#$&- {0}'.format(tweet['id']))
parameters = {
'neu_inf_lim': -0.3,
'neu_sup_lim': 0.3,
'language': 'spanish'
}
data = {
'name': (None, 'politic-bots'),
'parameters': (None, json.dumps(parameters), 'application/json'),
'data_object': (None, json.dumps(tweet_texts), 'application/json')
}
ret = []
logging.info('Computing the sentiment of {0} tweets'.format(
len(tweet_texts)))
resp = requests.post(url_sentiment, headers=headers, files=data)
if resp.status_code in error_codes:
# have to renew the api token
body_auth = {
'username': self.config['inhouse']['username'],
'password': self.config['inhouse']['password']
}
resp = requests.post(url_auth, data=body_auth)
if resp.status_code in accepted_codes:
resp_json = resp.json()
api_token = resp_json['token']
self.config['inhouse']['api_key'] = api_token
update_config(self.config_file_name, self.config)
resp = requests.post(url_sentiment,
headers=headers,
files=data)
else:
raise Exception(
'Error {0} when trying to renew the token of the api'.
format(resp.status_code))
if resp.status_code in accepted_codes:
resp_json = resp.json()
get_url = url_sentiment + str(resp_json['id']) + '/'
results = []
# wait some time before trying to get
# the results
time.sleep(60)
while len(results) == 0:
# wait some time before trying to
# get the results
time.sleep(30)
resp = requests.get(get_url, headers=headers)
if resp.status_code in accepted_codes:
resp_json = resp.json()
results = json.loads(resp_json['result'])
else:
raise Exception(
'Got an unexpected response, code: {0}'.format(
resp.status_code))
logging.info(
'Obtained the results of sentiment analysis, now the results are going to be processed...'
)
ret = self.__process_results(results)
else:
logging.error(
'Error {0} when trying to compute the sentiment of the tweets'.
format(resp.status_code))
logging.info('Computed correctly the sentiment of {0} tweets'.format(
len(tweet_texts)))
return ret
def __process_results(self, results):
ret = []
for result in results:
text, tone, score = result
if tone == 'neg':
sentiment = 'negative'
elif tone == 'pos':
sentiment = 'positive'
else:
sentiment = 'neutral'
tw_text_id = text.split('-$%#$&-')
id_tweet = tw_text_id[1].strip()
text_tweet = tw_text_id[0].strip()
dic_ret = {
'id': id_tweet,
'text': text_tweet,
'sentimiento': {
'tono': sentiment,
'score': score
}
}
ret.append(dic_ret)
return ret
class BotDetector:
__dbm_tweets = None
__dbm_users = None
__api = None
def __init__(self):
self.__dbm_tweets = DBManager('tweets')
self.__dbm_users = DBManager('users')
name_config_file = pathlib.Path(__file__).parents[1].joinpath('config.json')
conf = get_config(name_config_file)
auth = tweepy.AppAuthHandler(conf['twitter']['consumer_key'], conf['twitter']['consumer_secret'])
self.__api = tweepy.API(auth, wait_on_rate_limit=True, wait_on_rate_limit_notify=True)
def __save_user_pbb(self, user_screen_name, pbb, bot_score, user_bot_features, num_heuristics,
sum_weights, exist_user):
new_fields = {
'exists': int(exist_user),
'bot_analysis': {'features': user_bot_features,
'pbb': pbb,
'raw_score': bot_score,
'num_evaluated_heuristics': num_heuristics,
'sum_weights': sum_weights}
}
self.__dbm_users.update_record({'screen_name': user_screen_name}, new_fields)
def __check_if_user_exists(self, user_screen_name):
user_obj = self.__dbm_users.search({'screen_name': user_screen_name})[0]
if 'exists' in user_obj.keys():
return int(user_obj['exists'])
else:
try:
self.__api.get_user(user_screen_name)
return True
except tweepy.TweepError:
return False
def __compute_bot_formula(self, user_bot_features, exists_user):
name_weights_file = pathlib.Path(__file__).parents[0].joinpath('heuristic_weights.json')
weights_file = get_config(name_weights_file)
sum_heuristic_values = 0
sum_weights = 0
for feature_name in user_bot_features.keys():
feature_weight = weights_file[feature_name]
feature_value = user_bot_features[feature_name]['value']
sum_heuristic_values += feature_weight * feature_value
sum_weights += feature_weight
sum_heuristic_values += weights_file['exists'] * (1-int(exists_user))
sum_weights += weights_file['exists']
return sum_heuristic_values, sum_weights, sum_heuristic_values/sum_weights
def __get_timeline(self, user_screen_name, user_tweets):
"""
Get the last 100 tweets in the timeline of a given user
:param user: user from whom her timeline should be obtained from
:return: user's timeline
"""
user_obj = self.__dbm_users.search({'screen_name': user_screen_name})[0]
if 'timeline' in user_obj.keys():
return user_obj['timeline']
logging.info('Get the last 100 tweets from Twitter')
timeline = []
try:
for status in tweepy.Cursor(self.__api.user_timeline, screen_name=user_screen_name).items(100):
timeline.append(status._json)
# save the not electoral tweets of the user's timeline
id_electoral_tweets = [tweet['id_str'] for tweet in user_tweets]
timeline_tweets_to_save = [tweet for tweet in timeline
if tweet['id_str'] not in id_electoral_tweets]
logging.info('To save {0} not electoral tweets of {1}'.format(len(timeline_tweets_to_save),
user_screen_name))
new_field = {
'timeline': timeline_tweets_to_save
}
self.__dbm_users.update_record({'screen_name': user_screen_name}, new_field)
except tweepy.TweepError:
pass
return timeline
def __get_tweets_user(self, user_screen_name):
user_tweets_obj = self.__dbm_tweets.search({'tweet_obj.user.screen_name': user_screen_name})
user_tweets = [user_tweet_obj['tweet_obj'] for user_tweet_obj in user_tweets_obj]
return user_tweets
def __get_user_info_from_twitter(self, user_screen_name):
user_twitter_obj = None
try:
user_twitter_obj = self.__api.get_user(user_screen_name)
except tweepy.TweepError:
pass
return user_twitter_obj._json
def __get_computed_heuristics(self, user_screen_name):
user_obj = self.__dbm_users.search({'screen_name': user_screen_name})[0]
if 'bot_analysis' in user_obj.keys():
return user_obj['bot_analysis']['features']
else:
return {}
def __compute_heuristics(self, user_screen_name, recompute_heuristics=False):
logging.info('\n\nComputing the probability of being bot of the user: {0}\n\n'.format(user_screen_name))
# Get tweets of the user
user_tweets = self.__get_tweets_user(user_screen_name)
# Check if the user still exists on Twitter
exist_user = self.__check_if_user_exists(user_screen_name)
user_timeline = None
if exist_user:
# If the user still exists on Twitter, get her timeline
user_timeline = self.__get_timeline(user_screen_name, user_tweets)
# Get the information about the user and her tweets
user_obj = get_user(self.__dbm_tweets, user_screen_name)
if not user_obj:
user_obj = self.__get_user_info_from_twitter(user_screen_name)
if not user_obj:
raise Exception('Error!, Cannot fetch information about the user {0}'.format(user_screen_name))
if user_obj['verified']:
# It is a verified account, it cannot be bot
logging.info('The user {0} is an account verified by Twitter, it cannot be a bot'.format(user_screen_name))
self.__save_user_pbb(user_screen_name, 0, 0, None, 0, 0, exist_user)
return
# Get the computed heuristics
user_bot_features = self.__get_computed_heuristics(user_screen_name)
if user_bot_features:
user_computed_heuristics = user_bot_features.keys()
else:
user_computed_heuristics = []
if recompute_heuristics or 'retweet_electoral' not in user_computed_heuristics:
if user_tweets:
# Compute the percentage of retweets in the electoral tweets
per_rt = is_retweet_bot(user_tweets)
user_bot_features['retweet_electoral'] = {
'value': per_rt
}
if recompute_heuristics or 'reply_electoral' not in user_computed_heuristics:
if user_tweets:
# Compute the percentage of replies in the electoral tweets
per_rp = reply_percentage(user_tweets)
user_bot_features['reply_electoral'] = {
'value': per_rp
}
if recompute_heuristics or 'retweet_timeline' not in user_computed_heuristics:
# Compute the percentage of retweets in the user's timeline
if user_timeline:
per_rt = is_retweet_bot(user_timeline)
user_bot_features['retweet_timeline'] = {
'value': per_rt
}
if recompute_heuristics or 'reply_timeline' not in user_computed_heuristics:
if user_timeline:
per_rp = reply_percentage(user_timeline)
user_bot_features['reply_timeline'] = {
'value': per_rp
}
if recompute_heuristics or 'creation_date' not in user_computed_heuristics:
# Check the user's creation year
extraction_date = self.__dbm_tweets.find_record({})['extraction_date']
electoral_year = int('20' + extraction_date.split('/')[2])
user_bot_features['creation_date'] = {
'value': creation_date(parse_date(user_obj['created_at']), electoral_year)
}
if recompute_heuristics or 'default_profile' not in user_computed_heuristics:
# Check if the user has default profile.
user_bot_features['default_profile'] = {
'value': default_profile(user_obj)
}
if recompute_heuristics or 'default_profile_picture' not in user_computed_heuristics:
# Check if the user has default profile picture
user_bot_features['default_profile_picture'] = {
'value': default_profile_picture(user_obj)
}
if recompute_heuristics or 'default_background' not in user_computed_heuristics:
# Check if the user has default background picture
user_bot_features['default_background'] = {
'value': default_background(user_obj)
}
if recompute_heuristics or 'empty_description' not in user_computed_heuristics:
# Check if the user has a biography description
user_bot_features['empty_description'] = {
'value': default_description(user_obj)
}
if recompute_heuristics or 'location' not in user_computed_heuristics:
# Check if the user has location
user_bot_features['location'] = {
'value': location(user_obj)
}
if recompute_heuristics or 'ff_ratio' not in user_computed_heuristics:
# Check the user's following followers ratio
ratio = followers_ratio(user_obj)
user_bot_features['ff_ratio'] = {
'value': ratio
}
if recompute_heuristics or 'random_letters' not in user_computed_heuristics:
rl_value = random_account_letter(user_obj)
user_bot_features['random_letters'] = {
'value': rl_value
}
if recompute_heuristics or 'random_numbers' not in user_computed_heuristics:
rn_value = random_account_number(user_obj)
user_bot_features['random_numbers'] = {
'value': rn_value
}
if recompute_heuristics or 'similar_account' not in user_computed_heuristics:
similarity_score = similar_account_name(user_obj, self.__dbm_users, self.__dbm_tweets)
user_bot_features['similar_account'] = {
'value': similarity_score
}
# Compute the user's probability of being bot
num_computed_heuristics = len(user_bot_features.keys())
bot_score, sum_weights, pbb = self.__compute_bot_formula(user_bot_features, exist_user)
self.__save_user_pbb(user_screen_name, pbb, bot_score, user_bot_features,
num_computed_heuristics, sum_weights, exist_user)
logging.info('\n\nThe bot score of {0} is {1}\n\n'.format(user_screen_name, bot_score))
return
def compute_fake_promoter_heuristic(self, users):
name_weights_file = pathlib.Path(__file__).parents[0].joinpath('heuristic_weights.json')
weights_file = get_config(name_weights_file)
if not users:
users = self.__dbm_users.search({'bot_analysis.features.fake_promoter': {'$exists': 0},
'verified': {'$ne': True}})
tot_user = users.count()
idx_user = 1
for user in users:
logging.info('Remaining users: {0}'.format(tot_user - idx_user))
user_screen_name = user['screen_name']
user_obj = self.__dbm_users.search({'screen_name': user_screen_name})[0]
user_bot_features = user_obj['bot_analysis']['features']
# Check if the user interacts with bot accounts
fp = fake_promoter(user_screen_name, self.__dbm_users)
logging.info('User: {0}, fake promoter score: {1}'.format(user_screen_name, fp))
if not user_bot_features:
user_bot_features = {}
user_bot_features['fake_promoter'] = {
'value': fp
}
bot_score = user_obj['bot_analysis']['raw_score']
bot_score += user_bot_features['fake_promoter']['value'] * weights_file['fake_promoter']
heuristics = user_obj['bot_analysis']['num_evaluated_heuristics'] + 1
sum_weights = user_obj['bot_analysis']['sum_weights'] + weights_file['fake_promoter']
pbb = bot_score/sum_weights
exist_user = user_obj['exists']
self.__save_user_pbb(user_screen_name, pbb, bot_score, user_bot_features, heuristics, sum_weights,
exist_user)
idx_user += 1
def compute_bot_probability(self, users, source_users_collection = "", source_users_db = ""):
reusers_db = None
if source_users_db and source_users_collection:
reusers_db = DBManager(source_users_collection, source_users_db)
if not users:
# Get all users who don't have the analysis of bot in current user
users = self.__dbm_users.search({'bot_analysis': {'$exists': 0}})
tot_user = len(users) if type(users) == list else users.count()
idx_user = 1
for user in users:
logging.info('Remaining users: {0}'.format(tot_user-idx_user))
if reusers_db:
reuser_cursor = reusers_db.search({'screen_name': user['screen_name']})
if reuser_cursor.count() > 0:
logging.info('Reusing bot analysis from another DB for {0}'.format(user['screen_name']))
reuser = reuser_cursor[0]
bot_analysis = reuser['bot_analysis']
self.__save_user_pbb(reuser['screen_name'], bot_analysis['pbb'], bot_analysis['raw_score'],
bot_analysis['features'], bot_analysis['num_evaluated_heuristics'],
bot_analysis['sum_weights'], reuser['exists'])
continue
if type(users) == list:
user_screen_name = user
else:
user_screen_name = user['screen_name']
self.__compute_heuristics(user_screen_name)
idx_user += 1
def to_csv(self, output_file_name, include_verified_accounts=True):
if not include_verified_accounts:
query = {'bot_analysis': {'$exists': 1}, 'verified': {'$ne': True}}
else:
query = {'bot_analysis': {'$exists': 1}}
users = self.__dbm_users.search(query)
f_name = str(pathlib.Path(__file__).parents[2].joinpath('reports',output_file_name))
logging.info('Saving bot analysis into the csv file {0}'.format(f_name))
with open(f_name, 'w', encoding='utf-8') as f:
user_info_fields = ['screen_name', 'profile_url', 'party', 'movement', 'exists', 'followers',
'friends', 'tweets', 'rts', 'rps', 'verified']
bot_analysis_fields = ['location', 'default_profile_picture', 'retweet_electoral',
'default_background', 'similar_account', 'random_numbers', 'ff_ratio',
'random_letters', 'default_profile', 'creation_date', 'empty_description',
'retweet_timeline', 'reply_electoral', 'reply_timeline', 'fake_promoter',
'raw_score', 'sum_weights', 'pbb']
writer = csv.DictWriter(f, fieldnames=user_info_fields+bot_analysis_fields)
writer.writeheader()
tot_users = users.count()
logging.info('Going to save the information of the bot analysis of {0} users'.format(tot_users))
idx_user = 1
for user in users:
logging.info('Remaining users: {0}'.format(tot_users - idx_user))
row_dict = {}
for field_name in bot_analysis_fields:
if field_name in user['bot_analysis']['features'].keys():
row_dict[field_name] = user['bot_analysis']['features'][field_name]['value']
elif field_name in user['bot_analysis'].keys():
row_dict[field_name] = user['bot_analysis'][field_name]
for field_name in user_info_fields:
if field_name == 'profile_url':
continue
row_dict[field_name] = user[field_name]
if user['exists']:
row_dict['profile_url'] = 'https://twitter.com/' + user['screen_name']
else:
row_dict['profile_url'] = ' '
writer.writerow(row_dict)
idx_user += 1
logging.info('The saving process has finished, please check the file {0}'.format(f_name))