Using Pregel-like Large Scale Graph Processing Frameworks for Social Network Analysis

Pregel is a system for large scale graph processing developed at Google. It provides a scalable framework for running graph analytics on clusters of commodity machines. In this paper, we present several important undirected graph algorithms for social network analysis which fit within this framework. We discuss various graph componentisation methods, diameter estimation, degrees of separations, along with triangle, k-core and k-truss finding and computing clustering coefficients. Finally we present some experimental results using our own implementation of the Pregel framework, and examine key features of the general framework and algorithmic design.