Exploiting the topology property of social network for rumor detection

Information credibility gradually shown its significant influence on social networks with high propagation ability and low confidence threshold, leading to 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. Specially, we analyze the specific topology-related properties of user network, and confirm the impact on credibility evaluation. 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 previous studies 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.

[1]  Thomas W. McAvoy.  DON'T FOLLOW ME , 2009 .

[2]  Alex Hai Wang,et al.  Don't follow me: Spam detection in Twitter , 2010, 2010 International Conference on Security and Cryptography (SECRYPT).

[3]  Barbara Poblete,et al.  Information credibility on twitter , 2011, WWW.

[4]  Masahiro Kimura,et al.  Efficient Estimation of Influence Functions for SIS Model on Social Networks , 2009, IJCAI.

[5]  Jacob Ratkiewicz,et al.  Truthy: mapping the spread of astroturf in microblog streams , 2010, WWW.

[6]  W. Peterson,et al.  Rumor and Public Opinion , 1951, American Journal of Sociology.

[7]  P. Bordia,et al.  Rumor Psychology: Social and Organizational Approaches , 2006 .

[8]  M. Newman.  Spread of epidemic disease on networks. , 2002, Physical review. E, Statistical, nonlinear, and soft matter physics.

[9]  Marc Moonen,et al.  Seeing the Bigger Picture: How Nodes Can Learn Their Place Within a Complex Ad Hoc Network Topology , 2013, IEEE Signal Processing Magazine.

[10]  Nick Koudas,et al.  TwitterMonitor: trend detection over the twitter stream , 2010, SIGMOD Conference.

[11]  Patrick Paroubek,et al.  Twitter as a Corpus for Sentiment Analysis and Opinion Mining , 2010, LREC.

[12]  Horst D. Simon,et al.  Fast multilevel implementation of recursive spectral bisection for partitioning unstructured problems , 1994, Concurr. Pract. Exp..

[13]  Jiajia Wang,et al.  SIR rumor spreading model in the new media age , 2013 .

[14]  Andrew B. Kahng,et al.  New spectral methods for ratio cut partitioning and clustering , 1991, IEEE Trans. Comput. Aided Des. Integr. Circuits Syst..

[15]  Janyce Wiebe,et al.  Recognizing Contextual Polarity in Phrase-Level Sentiment Analysis , 2005, HLT.

[16]  Jean Carletta,et al.  Assessing Agreement on Classification Tasks: The Kappa Statistic , 1996, CL.

[17]  A. Noymer,et al.  The transmission and persistence of ‘urban legends’: Sociological application of age‐structured epidemic models , 2001, The Journal of mathematical sociology.

[18]  Setsuo Tsuruta,et al.  High Precision Credibility Analysis of Information on Twitter , 2013, 2013 International Conference on Signal-Image Technology & Internet-Based Systems.

[19]  Bo Pang,et al.  Thumbs up? Sentiment Classification using Machine Learning Techniques , 2002, EMNLP.

[20]  Barbara Poblete,et al.  Twitter under crisis: can we trust what we RT? , 2010, SOMA '10.

[21]  D. Zanette.  Dynamics of rumor propagation on small-world networks. , 2001, Physical review. E, Statistical, nonlinear, and soft matter physics.

[22]  Dragomir R. Radev,et al.  Rumor has it: Identifying Misinformation in Microblogs , 2011, EMNLP.

[23]  Scott Counts,et al.  Tweeting is believing?: understanding microblog credibility perceptions , 2012, CSCW.

[24]  Bojan Mohar,et al.  Laplace eigenvalues of graphs - a survey , 1992, Discret. Math..