Research and Evaluation on Modularity Modeling in Community Detecting of Complex Network Based on Information Entropy

Detecting the community of complex networks became the hot research fields of Graph Ming in recent years and most community detecting methods current try to find correct community structure basing on optimization of Modularity Q. In this article, the author constructs a new theoretic model of Q based on information entropy by simulation and evaluation on some classic dataset and comparison with the classic social network experimental results such as karate network, musicians network, email network and dolphin network by GN and Fast GN algorithm to cast some new light on community detecting. In the implementation, the author developed a visualization evaluation tool to analyze the community relationship in entities of complex networks in large scale mobile calling networks and gained some novel results in this area with visualization evaluation tool.