Open AccessWeighted network community division based on co-neighbor nodes and similarity
Author(s) -
Xiangfeng Luo,
Xin Sun,
Xiangyu Luo,
Yunzhong Luo
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1453/1/012126
Subject(s) - modularity (biology) , division (mathematics) , similarity (geometry) , cluster analysis , community structure , enhanced data rates for gsm evolution , computer science , data mining , function (biology) , weighted network , artificial intelligence , complex network , pattern recognition (psychology) , algorithm , mathematics , statistics , image (mathematics) , genetics , arithmetic , evolutionary biology , world wide web , biology
In order to realize the accuracy of weighted network community division, based on the analysis of existing weighted network community dividing algorithm, a community dividing algorithm based on co-neighbor nodes and similarity is proposed. Firstly, the similarity between nodes is defined, and the weight of the edge is added to the local modularity function. Secondly, the Burt structural hole principle is used to select the important nodes. Then, the local clustering method is used to continuously expand the community. Finally, the judgment is made. The change of the Local modularity determines whether to continue the clustering, so as to obtain a more accurate result. Experiments on the simulation dataset and Zachary’s Karate club dataset show that compared with the CRMA algorithm, the algorithm is effectively improved in weighted network division time and accuracy.