Detecting Overlapping Community in Complex Network Based on Node Similarity

Zuo Chen, Mengyuan Jia, Bing Yang, Xiaodong Li

Overlapping communities in complex network is a common phenomenon in real world network. The overlapping community structure can more accurately obtain the actual structure information in the network. But at present the study of overlapping community division algorithm is relatively less, facing the problems of the low accurate rate. Based on this, this paper presents algorithms OCNS for detecting community overlapping base on node similarity. The algorithm calculates similarity between two nodes in the network by means of Jaccard similarity measure formula. Then the related nodes are adaptive merged according to the similarity value, combining with the community according to the change of modularity. The process of partitioning can not only accurately merge closely linked nodes in the network, but also find the overlapping nodes and bridge nodes between communities. The experiment proved the algorithm is effective to detect the overlapping community and has obvious advantages in the division of baseline social network Zachary and dolphin network, and the quality of division better than other existing partitioning algorithm.