Congratulations to Dr. Jacob Ratkiewicz! Jacob successfully defended his dissertation titled The Expression of Human Behavior in Online Networks on May 2, 2011 and will take a position at Google in July. We will miss him!
Astroturfers, Twitter-bombers and smear campaigners need beware this election season as a group of leading Indiana University information and computer scientists today unleashed Truthy.indiana.edu, a sophisticated new Twitter-based research tool that combines data mining, social network analysis and crowdsourcing to uncover deceptive tactics and misinformation leading up to the Nov. 2 elections. Combing through thousands of tweets per hour in search of political keywords, the team based out of IU’s School of Informatics and Computing will isolate patterns of interest and then insert those memes (ideas or patterns passed by imitation) into Twitter’s application programming interface (API) to obtain more information about the meme’s history.
In the run-up to the mid-term elections, Truthy uncovered a number of abuses such as robot-driven traffic to politician websites and networks of bot accounts controlled by individuals to promote fake news. These findings have been widely covered in the press, with mentions in The Atlantic, MIT Technology Review, PC World, New Scientist, NPR, Ars Technica, Fast Company, The Chronicle of Higher Education, The New York Times Magazine, and many other media. Read more here and here.
Online popularity can be thought of as analogous to an earthquake; it is sudden, unpredictable, and the effects are severe. While shifts in online popularity are not inherently destructive – consider the unprecedented magnitude of online giving via Twitter following the disaster in Haiti – they indicate radical swings in society’s collective attention. Given the increasingly profound effect that large-scale opinion formation has on important phenomena like public policy, culture, and advertising profits, understanding this behavior is essential to understanding how the world operates.
In this paper by Ratkiewicz and colleagues, the authors put forth a web-wide analysis that includes large-scale data sets of the online behaviors of millions of people. The paper offers a novel model that is is capable of reproducing all of the observed dynamics of online popularity through a mechanism that causes sudden, nonlinear bursts of collective attention. These results have been mentioned in the APS and PhysOrg websites.
NaN folks were busy during the summer. First, we descended to Riva del Garda for Sunbelt XXX, the social networks conference. Rossano presented a poster on social link prediction from shared metadata (with Alain, Ciro, Ben, Fil); Fil presented a paper on Scholarometer (with Diep); and Sandro presented a paper on Wikipedia traffic modeling (with Jacob and Fil). Then Lilian went to Wshington, DC where she presented a poster on social games with a purpose at HCOMP2010. Finally, Jacob presented two papers on traffic in social media (with Sandro, Fil, Santo, and Alex) at the SocialCom2010 International Symposium on Social Intelligence and Networking (SIN-10) in Minneapolis. Congratulations to everyone for the great work!
I will talk about some work related to to the problem of predicting the popularity of online content, and some initial results from my experiments in this area. More in detail, I’ll overview work by Leskovec et al and Huberman et al on modeling and predicting growth, then outline the results of two initial experiments.