Estimating The Optimal Number Of Communities By Cluster Analysis

How to identify community structure in complex network is of theoretical significance, which relates to help to analyze the network topology and understand the network works. Determining the optimal number of communities is a nontrivial problem in detecting community structure. In this paper, we propose a novel method for detecting the optimal number of communities. Based on the local random walk (LRW) measurement, the distance index between each pair of nodes of a network is calculated firstly. Then the optimal number of communities can be found based on the idea that community centers are characterized by a higher density than their neighbors and by a relatively large distance from nodes with higher densities. The experimental results show that the method is effective and efficient in both artificial and real-world networks.