Topic-aware Interaction-centric Overlapping Community Detection and Profiling in the Microblog
Zhu Wang, Bin Feng, Zhiwen Yu and Bin Guo
With the recent surge of microblogging services, such as Twitter and Sina Weibo, huge digital footprints of the user’s profiles, tweets and comments, and online social interactions become accessible to service providers. Unlike social networks (e.g., Facebook, Flickr) that have explicit groups for users to subscribe to or join, microblogs usually have no explicit community structures. In order to capitalize on the large number of potential users, quality community detection and profiling approaches are needed. In the meantime, the diversity of users’ interests and behaviors when using microblogs suggests that their community structures overlap. In this paper, based on the user’s online social interactions (e.g., tweeting, retweeting) and textual information (e.g., tweets, retweets), we come out with a novel topic-aware and interaction-centric hypergraph clustering approach to discover and profile the overlapping communities of microblog users. By employing both pairwise and triadic hyperedges, the proposed framework is not only able to group like-minded users from different social perspectives but also discover communities with explicit profiles indicating the interests of community members. The efficacy of our approach is validated by intensive empirical evaluations using the collected Sina Weibo dataset.
Keywords: Topic; interaction; community detection; community profiling; hypergraph clustering