Finding true and credible information on Twitter

In this paper, we present a unique study of two successful methods for computing message reliability. The first method is based on machine learning and attempts to find a predictive model based on network features. This method is generally geared towards assessing credibility of messages and is able to generate high recall results. The second method is based on a maximum likelihood formulation and attempts to find messages that are corroborated by independent and reliable sources. This method is geared towards finding facts in which humans are treated as binary sensors and is expected to generate high accuracy results but only for those facts that have higher level of corroboration. We show that these two methods can point to similar or quite different predictions depending on the underlying data set. We then illustrate how they can be fused to capture the trade off between favoring true versus credible messages which can either be opinions or not necessarily verifiable.

[1]  Sibel Adali,et al.  Actions speak as loud as words: predicting relationships from social behavior data , 2012, WWW.

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

[3]  Sibel Adali,et al.  Understanding Information Credibility on Twitter , 2013, 2013 International Conference on Social Computing.

[4]  Soo Young Rieh,et al.  Developing a unifying framework of credibility assessment: Construct, heuristics, and interaction in context , 2008, Inf. Process. Manag..

[5]  Charu C. Aggarwal,et al.  Using humans as sensors: An estimation-theoretic perspective , 2014, IPSN-14 Proceedings of the 13th International Symposium on Information Processing in Sensor Networks.

[6]  Tobias Höllerer,et al.  Modeling topic specific credibility on twitter , 2012, IUI '12.

[7]  Ed H. Chi,et al.  Want to be Retweeted? Large Scale Analytics on Factors Impacting Retweet in Twitter Network , 2010, 2010 IEEE Second International Conference on Social Computing.

[8]  Tarek F. Abdelzaher,et al.  On truth discovery in social sensing: A maximum likelihood estimation approach , 2012, International Symposium on Information Processing in Sensor Networks.

[9]  S. Gosling,et al.  Should we trust web-based studies? A comparative analysis of six preconceptions about internet questionnaires. , 2004, The American psychologist.

[10]  Arun Sundararajan,et al.  Distinguishing influence-based contagion from homophily-driven diffusion in dynamic networks , 2009, Proceedings of the National Academy of Sciences.

[11]  J. O'Donovan,et al.  Cutting Through the Noise : Defining Ground Truth in Information Credibility on Twitter , 2013 .

[12]  Kevin Robert Canini,et al.  Finding Credible Information Sources in Social Networks Based on Content and Social Structure , 2011, 2011 IEEE Third Int'l Conference on Privacy, Security, Risk and Trust and 2011 IEEE Third Int'l Conference on Social Computing.

[13]  Hengchang Liu,et al.  Exploitation of Physical Constraints for Reliable Social Sensing , 2013, 2013 IEEE 34th Real-Time Systems Symposium.

[14]  Ponnurangam Kumaraguru,et al.  Credibility ranking of tweets during high impact events , 2012, PSOSM '12.

[15]  Sibel Adali,et al.  Credibility in Context: An Analysis of Feature Distributions in Twitter , 2012, 2012 International Conference on Privacy, Security, Risk and Trust and 2012 International Confernece on Social Computing.

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