A method to detect communities with stability in social networks

Abstract

We propose stable community detection (SCD), a framework to effectively identify stable communities in online social networks (OSNs). Our framework works by first enriching the input network with the mutual relationship estimation of all links and then discovering stable communities using a lumped Markov chain model. SCD has the advantage of handling the real model of OSNs with weighted reciprocity relationships. This approach is also supported by a key connection between the persistence probability of a community and its local topology.To certify the efficiency and stability of the discovered communities, we test SCD on both synthesized datasets and real-world social traces, including the NetHEPT collaboration, Foursquare, Twitter and Facebook social networks, in reference to the consensus of other state-of-the-art detection methods. Competitive experimental results confirm the quality and efficacy of the proposed framework on identifying stable communities in OSNs.