MCD: Mutually Connected Community Detection using clustering coefficient approach in social networks

The recognition of communities from social networks is a remarkable and purposeful thing to be determined. Several past studies agonized from insufficient methods for the detection mechanism of communities in the given network due to the different variables influencing social networks and a large amount of the complexity to be manipulated, caused by the high scaling structures of these networks. Therefore, the analysis of social networks is enhancing the linkage between social spaces. Community detection is a vital problem to be solved in analyzing the social network. consumers or simply the users in a social network ordinarily consists of some regular social communication or interaction in simple, with their own friends or connected peoples residing in a particular community due to their common interests or almost similar profiles. In this paper, an efficient process, MCD(Mutual Community Detection) is proposed. The proposed approach is then applied to datasets of U.S Airline companies and Zachary Karate Club using the clustering coefficient approach. This approach detects the community of strongly mutually connected components having different values of the relation residing in the network. Experimental results demonstrated that components having a higher value of clustering coefficient are strongly connected and form a community of mutual connectivity. In addition, density and average degree communities were also investigated. Experimentation conducted on the two, human social and real data-sets reveal the effectiveness and the efficiency of our proposed method.