TSCDA: a dynamic two-stage community discovery approach

In this paper, we introduce a new approach for detecting community structures in networks. The approach is subject to modifying one of the connectivity-based community quality functions based on considering the impact that each community's most influential node has on the other vertices. Utilizing the proposed quality measure, we devise an algorithm that aims to detect high-quality communities of a given network based on two stages: finding a promising initial solution using a greedy method and then refining the solutions in a local search manner. The algorithm's performance has been evaluated on various standard real-world networks and artificial graphs. The quality of the results has been reported and compared with those obtained by several state-of-the-art algorithms. As it turns out, the proposed approach is competitive with the other well-known techniques in the literature and significantly outperforms them.