基于核心图聚类的邮件网络社区发现

A mail community partition based on coring graph clustering

根据图聚类节点的密度变化确定核心节点,构成连通子图并确定邮件网络社区划分的个数及初始社区中心点,通过社区中心动态调整的方法将非核心节点划分至所属社区。实验证明了该邮件网络社区划分的有效性和可行性。

Based on the greedy algorithm with graph clustering by computing the density variation sequence and identifying core nodes, number of communities, partition the certain nodes to some belonged community with the similarity of characteristics of communication behavior, and readjust the centrality of the communities. The real datasets shows the feasibility and effectiveness of the proposed algorithm.