Research of Overlap Community Detection Algorithm Based on Time-Weighted

With the continuous expansion and complexity of network structure, overlapping community discovery technology is of great significance to excavate the deep potential structure of complex network. This article presents an overlapping community detection algorithm based on time time-weighted. Considering the time factor of user interest, this method constructs a user-user graph with time-weighted links. Then, the global similarity of users is calculated based on the influence of network nodes. On this basis, the centrality of nodes is calculated as an important index to measure the impact of nodes on community structure, and a method to select community centers is proposed. Finally, overlapping community detection is realized by iteration of utility function. The proposed algorithm is validated by artificial network and real network. The experimental results show that compared with traditional community discovery methods, the proposed algorithm outperforms many existing overlapping community discovery algorithms in terms of community discovery quality and computational efficiency. Copyright © 2021 Acta Automatica Sinica. All rights reserved.