Exploting The Topology Property Of Social Netword For Information Credibility

Due to the rapid development of internet,information credibility has gradually shown its significant influence on social networks,with high propagation ability and low confidence threshold,resulting in serious damage to the trust system in social network and the crucial work of identifying rumors.In this paper,we address the special characteristics of Weibo,the most popular microblogging service in China like Twitter,and proposed a general framework to assess the credibility of information.Information credibility in social network mainly reflect in the uncertainty of user identity and text information.This paper consider both the property feature and the behavior feature of user to distinguish legitimate user and spam user in social network.Based on the features with high information gain,the user credibility can be measured with machine learning algorithm.Sentiment classification is used to detect the text information credibility.With the judgment and emotion polarity of text written by users,information credibility can be weighted.Specially,we analyze the specific topology-related properties of user network,which could uncover the hidden relationship between reviewers and achieve the rationalization of impact factors,leading to a more objective evaluation in rumor detection.We use features extracted from the microblogs,from the text of the reviews,and from the network structures.To explore the effectiveness of our approach,we conduct the experiment based on an extensive set of data provided by the community of management center in Weibo.Our results reveal that features considered in this study achieve a better performance with the consideration of new features we proposed.We believe the work in this paper open new dimensions in analyzing online disinformation.