Discovery and analysis of tightly knit communities in telecom social networks

Abstract

Community identification has been a major research area in social network analysis. One popular type of community is one in which every member of the community knows every other member, which can be viewed as a clique in a graph representing the social network. In this paper, we present a novel highly scalable method for finding large maximal cliques that is validated with experimental results on several real-life social networks. In addition, while the importance of finding tightly knit communities has been widely accepted, the influence of community on the behavior of the individuals belonging to those communities is relatively unexplored. We also attempt to answer various questions in the context of cliques as communities in telecom social networks: how individuals in communities behave, what influence a community has on the behavior of an individual, and whether communities have a characteristic behavior of their own. We also examine whether the behavior of individuals who belong to communities differs from those who do not. We believe that the findings of such a study will reassert the importance of finding communities in telecom social networks and will help telecom operators improve group targeting and customer relationship management. © 2010 IBM.