Detection of Temporal Communities in Mobile Social Networks

In recent years, community detection in Mobile Social Networks (MSNs) has attracted a lot of attentions from both academia and industry areas. The existing methods of community detection usually focus on static networks. However, MSNs in essence are dynamically intermittently connected networks with a time-varying topology. Therefore, this paper proposes a novel temporal community detection method based on nodes' temporal closeness. In order to evaluate the performance of the proposed method and study the evolution law of the temporal community, we conduct extensive simulations using two real mobility traces, the MIT Reality trace and the Infocom 06 trace. The results show that many temporal communities share similar members and appear at different times. Furthermore, we find the periodic appearance of temporal community.