The network you keep: Analyzing persons of interest using cliqster

We consider the problem of determining the structural differences between different types of social networks and using these differences for applications concerning prediction of their structures. Much research on this problem has been conducted in the context of social media such as Facebook and Twitter, within which one would like to characterize and classify different types of individuals such as leaders, followers, and influencers. However, we consider the problem in the context of information gathered from law-enforcement agencies, financial institutions, and similar organizations, within which one would like to characterize and classify different types of persons of interest. The members of these networks tend to form special communities and thus new techniques are required. We propose a new generative model called Cliqster, for unweighted networks, and we describe an interpretable, and efficient algorithm for representing networks within this model. Our representation preserves the important underlying characteristics of the network and is both concise and discriminative. We demonstrate the discriminative power of our method by comparing to a traditional SVD method as well as a state-of-the-art Graphlet algorithm. Our results are general in that they can be applied to “person of interest” networks as well as traditional social media networks.