Rumors detection in Chinese via crowd responses

Abstract

In recent years, microblogging platforms have become good places to spread various spams, making the problem of gauging information credibility on social networks receive considerable attention especially under an emergency situation. Unlike previous studies on detecting rumors using tweets' inherent attributes generally, in this work, we shift the premise and focus on identifying event rumors on Weibo by extracting features from crowd responses that are texts of retweets (reposting tweets) and comments under a certain social event. Firstly the paper proposes a method of collecting theme data, including a sample set of tweets which have been confirmed to be false rumors based on information from the official rumorbusting service provided by Weibo. Secondly clustering analysis of tweets are made to examine the text features extracted from retweets and comments, and a classifier is trained based on observed feature distribution to automatically judge rumors from a mixed set of valid news and false information. The experiments show that the new features we propose are indeed effective in the classification, and especially some stop words and punctuations which are treated as noises in previous works can play an important role in rumor detection. To the best of our knowledge, this work is the first to detect rumors in Chinese via crowd responses under an emergency situation.

Rumor Identification in Microblogging Systems Based on Users’ Behavior

“…In [12], Sun et al first proposed multimedia-based features for event rumors identification. Cai et al [13] proposed text features from retweets and comments to construct rumor classifier. Wang et al [14] proposed graph-based features and applied them in spam bots detection.…”

Exploiting Context for Rumour Detection in Social Media

“…The approach has been to train a classifier from a labelled set of tweets to categorise the stance observed in new tweets discussing rumours; however, these authors do not deal with nonrumours, assuming instead that the input to the classifier is already cleaned up to include only tweets related to rumours. There is also work on veracity classification both in the context of rumours and beyond [4,14,15,19,33,18,12]. Work on stance and veracity classification can be seen as complementary to our objectives; one could use the set of rumours detected by a rumour detection system as input to a classifier that determines stance of tweets in those rumours and/or veracity of those rumours [36].…”

Detecting Rumors Through Modeling Information Propagation Networks in a Social Media Environment

“…Their work particularly explored the problem of picture misuse as a source of rumors. For readers interested in more studies regarding rumor propagation and detection on Sina Weibo, they are referred to [9][10][11][12].…”