Joint non-negative matrix factorization for community structures detection in signed networks

Zhong-Yuan Zhang, Chao Yan, Hui-Min Cheng, Xin Liu

Abstract: Community structures detection in signed networks is crucial for understanding not only the topology structures of signed networks but also the functions of them, such as information diffusion, epidemic spreading, etc. In this article, we develop a joint non-negative matrix factorization model to detect community structures. Also, we propose a modified partition density to evaluate the quality of community structures, and use it to determine the appropriate number of communities. Finally, the effectiveness of our approach is demonstrated based on both synthetic and real-world networks.