A parallel and distributed algorithm for role discovery in large-scale social networks

By analyzing large-scale number of human behavior data, we propose a new parallel and distributed algorithms for social role discovery based on dynamic and fine-grained human behavior attributes in social networks. We first mining and propose number of properties that on behalf of human behavior. After that, to deal with the large human behavior data, a simple, scalable and distributed parallel clustering algorithm based on grid and density is developed. The theoretical analysis and experimental results show that the algorithm has better efficiency and effectiveness, and algorithms reveals valuable discovery on the real-life datasets. Besides, the methodology in this paper for user role discovery also can be applied to social networks in general.