An efficient local algorithm for overlapping community detection in social networks

Community detection represents the most active fields in social network analysis. This paper focuses on the identification of overlapping communities. The main two phases of the proposed method are the selection of the initial communities and their expansion. A new weighted belonging degree is proposed two develop the level of accuracy. The evaluation of results is performed by exploiting the overlapping version of modularity and the normalized mutual information. Experimentation on different synthetic and real networks show the high quality of the resulted communities.