Discovering Multiple Social Ties for Characterization of Individuals in Online Social Networks

Online social network services now have generally enormous monthly active users. Each user may have hundreds of different ties to families, friends or acquaintances. Discovering multiple social ties is pivotal in understanding the human relationship and recognizing the role played by individuals in very large networks. In this paper, an incremental Dirichlet process Gaussian mixture model is introduced to automatically cluster social ties in a dynamic social network. We demonstrate that individuals can be characterized by the combination of discovered multiple social ties, which is a profile that directly links to the role played by an individual in a given social network. Compared to other existing methods, our approach achieves a superior accuracy on real networks.