All posts by midconov

2011 Truthy Updates

WSJ video on Truthy project
Mike Conover in the WSJ's report on the Truthy project

We’re pleased to report several exciting developments in our interdisciplinary project studying information diffusion in complex online social networks. The past year has resulted in several publications. Our results on the Truthy astroturf monitoring and detection system were presented at WWW 2011 and ICWSM 2011. Research into the polarized network structure of political communication on Twitter was presented at ICWSM and received the 2011 CITASA Best Student Paper Honorable Mention. We demonstrated the feasibility of the prediction of individuals’ political affiliation from network and text data (SocialCom 2011), a machine learning application that enables large-scale instrumentation of nearly 20,000 individuals’ political behaviors, policy foci, and geospatial distribution (Journal of Information Technology and Politics). We’re also working on a paper on partisan asymmetries in online political activity surrounding the 2010 U.S. congressional midterm elections.

Our results have been widely covered in the press, including the Wall Street JournalScienceCommunications of the ACM, NPR [1,2], The Chronicle of Higher Education, Discover Magazine, The Atlantic, New ScientistMIT Technology Review, and many more.

Current and future research is supported by an award from the NSF Interface between Computer Science and Economics & Social Sciences program, and a McDonnell Foundation grant. The former will focus on building an infrastructure for the study of information diffusion in social media, the characterization of meme spread patterns, and the development of sentiment analysis tools for social media. The latter will focus on modeling efforts, especially agent-based models of information diffusion, competition for attention, and the relationship between information sharing events and social network evolution.

NaN Abstract for Michael Conover’s April 21st Talk

“The problem with Wikipedia is that it only works in practice. In theory, it can never work.”  — Zeroeth Law of Wikipedia

One of the most important social and intellectual phenomena of the 21st century, the collaboratively-edited online encyclopedia Wikipedia is vexing in its ability to produce informative articles on a multitude of subjects.  Leveraging graph theoretic techniques to measure the degree to which latent connections between articles are present in the Wikipedia corpus we demonstrate that the collaborative editing process produces, over time, an increasingly logically-connected information artifact. Moreover, using the public-domain 1911 Encyclopedia Britannica as a benchmark corpus for the single-author-article paradigm, we demonstrate that Wikipedia contains a growing core of mature articles which exhibit a degree of logical connectedness significantly surpassing that found in the Encyclopedia Britannica. Taken in conjunction with an understanding of Wikipedia’s accuracy and topical coverage, this conclusion paints a rich portrait of the strengths and weaknesses of both collaboratively- and single-author-edited encyclopedias.