Community Mining Algorithm Based on Structural Similarity

摘要

In order to improve the efficiency of community mining algorithm and the accuracy of community classification, a community mining algorithm based on structural similarity is proposed in this paper. The algorithm uses the structural similarity as an edge weight to perform the operation of the loop deletion, and implements community merging for isolated nodes, thus improving the precision of community division. The algorithm is compared with GN and SSNCA algorithm in classic data sets such as Zachary network, football data and dolphin social network. The experimental results show that the algorithm can effectively detect the community structure in complex networks, and the accuracy of classification and operation speed are obviously improved.