SE-CDA: A scalable and efficient community detection algorithm

Abstract

Detecting communities is of great importance in various disciplines such as social media, biology and telephone networks, where systems are often represented as graphs. Community is formed by individuals such that those within a group interact with each other more frequently than with those outside the group. The communities have different properties such as node degree, betweenness, centrality, cluster coefficient and modularity. Discovering communities from social networks of big data scale on a single se quential machine is a tedious task. In this paper, we present a Scalable Community Detection Algorithm which relaxes the performance issues due to many I/Os. We adopt Girvan-Newman's modularity based hierarchical community detection algorithm in bottom u p a pproach an d proposed an approximation algorithm for community detection in a distributed environment. We developed our approach using MapReduce and Giraph computing platforms. Experimental results demonstrate that the proposed approach is more efficient than standard MapReduce approach and easily scaled to graph of any size.