A Novel Community Detection Method for Collaborative Networks

Community structure prevails in network graphs like social networks, web graphs and collaborative networks. Clique percolation is one popular method used for unfolding the community structure in networks. However, clique percolation method is inefficient as the computational time is high for merging the identified cliques. This paper proposes a novel technique for detecting overlapping community structure by addressing the problem of clique merging. We reduce the overall time for community detection by applying edge streaming technique. The proposed method is validated through experiments using real and synthetic data in comparison with conventional clique percolation algorithm. The performance parameters such as execution time and goodness of the cluster are used for comparison and the results are promising. This model is suitable for community detection in collaborative network.

I. Introduction

A network is a collection of interconnected entities, usually consists of nodes and edges. These networks can be simple as well as complex. Networks, sometimes also called as graphs have a great importance in modern network science. Graphs are used in many areas of modern science like biology and chemistry for representing bonds between molecules. Another application of graphs is in sociology, which is the study of structure of human society. A complex network is a large graph of real life. The complex networks [1] include biological networks, Internet and social networks. The study on graph structure for analyzing the relationships between entities yield useful applications [2]. It is difficult to analyze complex networks as we cannot predict how the entities are linked. So to analyze large complex networks, a community structure needs to be formed. Fig. 1 depicts generic work flow of community detection and analysis. Study of complex network using community structure could unfold the entity relationships and patterns.