CILPA: a cohesion index based label propagation algorithm for unveiling communities in complex social networks

Social network analysis is the process of recording various patterns of interactions between a set of social entities. An important phenomenon that draws the attention of analysis is the emergence of communities in these networks. The understanding and identifying communities in these networks is challenging and has gained much importance these days. There are many approaches suggested to identify communities in social networks, and most of them are time consuming when implemented or need some important user-input parameters. In this paper, a new label propagation algorithm named CILPA (Cohesion Index based Label Propagation Algorithm) is proposed. The algorithm brings in two new functions, called Cohesion Similarity (CoSim) and Cohesion Index (CI). The cohesion index function measures cohesiveness of nodes and similarity with neighbor nodes is measured using cohesion similarity. Cohesion index as the base, we propose a new label propagation algorithm with precise node update sequence and node priority. Prior information about the number of communities is not required in our algorithm and the results show that the quality of communities obtained by CILPA are very stable and better than those detected by original LPA. Results of experiments conducted on real world networks demonstrate the efficiency of our approach and indicate that cohesion index calculation of nodes improves the accuracy and CILPA is an efficient method for unveiling communities in complex social networks. © 2018, Bharati Vidyapeeth's Institute of Computer Applications and Management.