A simulation method for social networks

With the increasing popularity of social networks, it is becoming more and more crucial for the decision makers to analyze and understand the evolution of these networks to identify for example, potential business opportunities. Unfortunately, understanding social networks, which are typically complex and dynamic, is not an easy task. In this paper, we propose an effective and practical approach for simulating social networks. We first develop a social network model that considers growth and connection mechanisms (including addition and deletion) of social networks. We consider the nodes’ in-degree, inter-nodes’ close degree which indicates how close the nodes are in the social network, which is limited by the in-degree threshold. We then develop a graph-based stratified random sampling algorithm for generating an initial network. To obtain the snapshots of a social network of the past, current and the future, we further develop a close degree algorithm and a close degree of estimation algorithm. The degree distribution of our model follows a power-law distribution with a “fat-tail”. Experimental results using real-life social networks show the effectiveness of our proposed simulation method.