Jointly Modeling Community and Topic in Social Network

Social networks contain not only link information, but also text information. It is an important task to discover communities in social network analysis. Moreover, it is helpful to understand the community by finding its topics of interest. In fact, social networks are always dynamic. However, there are still few method to detect communities and their topics by combining link and text information in dynamic network. In this paper, we formulate the problem of detecting communities and their topics and propose a dynamic topical community detection (DTCD) method to solve the problem. DTCD integrates link, text and time in a unified way by using generative model. The community and the topic are modeled as latent variables which are learned by collapsed Gibbs sampling. DTCD can not only find communities and their topics, but also capture the temporal variations of communities and topics. Experimental results on two real-world datasets demonstrate the effectiveness of DTCD.