Evolutionary Community Detection in Dynamic Social Networks

• Published in: 2019 International Joint Conference on Neural Networks (IJCNN) pp. 1 - 7
• Main Authors: Liu, Fanzhen, Wu, Jia, Zhou, Chuan, Yang, Jian
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01-07-2019
• Subjects: Conductivity; Genetic algorithms; Genetics; Heuristic algorithms; Mathematical model; Optimization; Social networking (online)
• ISSN: 2161-4407
• DOI: 10.1109/IJCNN.2019.8852006

Evolutionary clustering is a way of detecting the evolving patterns of communities in dynamic social networks. In principle, the detection process seeks to simultaneously maximize clustering accuracy at the current time step and minimize the clustering drift between two successive time steps. Several evolutionary clustering methods have been developed in an attempt to find the best trade-off between clustering accuracy and temporal smoothness, but the classic genetic operators in these methods do not make the best of the inter- and intra-connected relationships between nodes, which limits their effectiveness. To overcome this problem, we propose a novel migration operator to work in tandem with classic genetic operators to improve the discovery of evolving community structures. The operator is implemented within an existing genetic algorithm which relies on a genome representation under a decomposition framework that formulates evolutionary community detection as a multiobjective optimization problem. Moreover, we present a new method of calculating modularity directly from a genome matrix as the objective for measuring the snapshot quality, which results in a wider search space for finding the optimal solution. Experimental results over several synthetic networks and one real-world dynamic social network suggest that our method is superior to two other state-of-the-art methods in terms of both accuracy and smoothness in discovering evolving community structures in dynamic social networks.