Abstract

We propose an automated and unsupervised method-ology for a novel summarization of group behavior based on content preference. We show that graph the-oretical community evolution (based on similarity of user preference for content) is effective in indexing these dynamics. Combined with text analysis that tar-gets automatically-identified representative content for each community, our method produces a novel multi-layered representation of evolving group behavior. We demonstrate this methodology in the context of politi-cal discourse on a social news site with data that spans more than four years and find coexisting political lean-ings over extended periods and a disruptive external event that lead to a significant reorganization of exist-ing patterns. Finally, where there exists no ground truth, we propose a new evaluation approach by using en-tropy measures as evidence of coherence along the evo-lution path of these groups. This methodology is valu-able to designers and managers of online forums in need of granular analytics of user activity, as well as to re-searchers in social and political sciences who wish to extend their inquiries to large-scale data available on the web. 1