Community structure detection based on node merging information entropy

In order to solve the problems of high complexity and low division accuracy of the current community division, a new community structure detection algorithm is proposed from the perspective of information entropy theory. In view of the uncertainty of the occurrence of node division probability system events, the similarity index is used to calculate the information provided by node combination, and the further construction of node merge information entropy model is made by combining the global importance degree. The value of the entropy function is used to judge the merging scheme with the least uncertainty. Apply the idea of hierarchical clustering to realize the final community division. Through the comparison and analysis of real network datasets, the effectiveness of the algorithm is verified, and the divided community has a high degree of modularity.