A New Method for Identifying Detected Communities Based on Graph Substructure

• Authors: Shumei Kameyama;Makoto Uchida;Susumu Shirayama
• Venue: WI-IATW '07 Proceedings of the 2007 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology - Workshops
• Year: 2007

Many methods have been developed that can detect community structures in complex networks. The detection methods can be classified into three groups based on their characteristic properties. In this study, the inherent features of the detection methods were used to develop a method that identifies communities extracted using a given community detection method. Initially, a common detection method is used to divide a network into communities. The communities are then identified using another detection method from adifferent class. In this paper, the community structures are first extracted from a network using the method proposed by Newman and Girvan. The extracted communities are then identified using the proposed detection method that is an extension of the vertex similarity method proposed by Leicht et al. The proposed method was used to identify communities in a blog network (blogosphere) and in a Wikipedia wordnetwork.