Study on similarity based on connection degree in social network

Abstract

Application of set pair analysis theory, the social network is as an identical---discrepancy---contrary system. Firstly, based on connection degree to descript the identical---discrepancy---contrary relation between vertices, considering the contribution of local features and the topological structure to the similarity between vertices, we define the similarity based on connection degree taking into account weight and clustering coefficient. The similarity can better describe network structure characteristics, overcome the under-estimating for the local similarity indices, and reduce the computational complexity of the global indices. Secondly, in order to apply the similarity to community discovery, combined with agglomerative hierarchical clustering algorithm, we propose a new community discovery algorithm Vertices Similarity First and Communities Mean (VSFCM), so that it is applicable to detect community structures in complex networks with any object that has similarity. Finally, the correctness and effectiveness of the similarity measurement and algorithm VSFCM are terrified through the experiments.