Infinite Hierarchical MMSB Model for Nested Communities/Groups in Social Networks

TL;DR

This paper introduces an infinite hierarchical MMSB model that captures multi-faceted roles and nested community structures in social networks, enabling automatic discovery of complex social hierarchies.

Contribution

It proposes a novel hierarchical mixed membership stochastic blockmodel with a Gibbs sampling algorithm for uncovering latent social hierarchies and role-specific interactions.

Findings

Successfully models nested communities in synthetic networks

Effectively uncovers hierarchies in real-world predator-prey networks

Demonstrates utility in citation network analysis

Abstract

Actors in realistic social networks play not one but a number of diverse roles depending on whom they interact with, and a large number of such role-specific interactions collectively determine social communities and their organizations. Methods for analyzing social networks should capture these multi-faceted role-specific interactions, and, more interestingly, discover the latent organization or hierarchy of social communities. We propose a hierarchical Mixed Membership Stochastic Blockmodel to model the generation of hierarchies in social communities, selective membership of actors to subsets of these communities, and the resultant networks due to within- and cross-community interactions. Furthermore, to automatically discover these latent structures from social networks, we develop a Gibbs sampling algorithm for our model. We conduct extensive validation of our model using synthetic networks, and demonstrate the utility of our model in real-world datasets such as predator-prey networks and citation networks.