Community detection across multiple social networks based on overlapping users

With the rapid development of Internet technology, online social networks have got fast development and become increasingly popular. Meanwhile, the research works across multiple social networks attract growing attention, among which community detection is quite important for online security problems, such as the user behavior analysis and abnormal community discovery. In this paper, a community detection method is proposed across multiple social networks based on overlapping users. First, the concept of overlapping users is defined, then an algorithm CMN_NMF is designed to discover the stub communities from overlapping users based on the social relevance. After that, we expand each stub community in different social networks by adding the users with strong similarity, and in the end different communities are derived out across networks. At last, experiments are carried out to verify the reasonability of community. Our method shows better performance in real datasets compared with others.