A neighbour-similarity based community discovery algorithm

Abstract

Discovery of communities in a network is a non-trivial task. Recently, many similarity functions have been introduced to cluster nodes of the same type, but tightness relationship between the nodes inside the clusters always remained as an issue. Another important issue is that for some difficult cases like selecting a community for a node that equally belongs to more than one community which may create an ambiguity in determining the node’s best-fit community remain unaddressed in many community discovery algorithms. A single wrong prediction about a node’s community may lead to an incorrect prediction for other nodes, resulting in a poor community structure. To address such issues, a Neighbour Based Community Detection(NBCD) algorithm based on two novel similarity measures using a similarity parameter α and a set of ground rules are proposed in this work. The similarity parameter α provides a choice for the user to select the tightness of the nodes within the communities. The NBCD algorithm is a two-step process: one is community detection and the next is node shifting. Extensive experiments are carried out on real-world benchmark data sets and artificial networks to assess the performance of the proposed algorithm. NBCD algorithm is compared with several recent and state-of-the-art community discovery algorithms. Normalized Mutual Information(NMI), Adjusted Mutual Information(AMI), Adjusted Rand Index(ARI), F-measure and Modularity are used as the performance measures. Experimental results prove that the proposed algorithm, NBCD, performs well with respect to all the performance measures and performs better than the other community detection algorithms considered.