Community Detection in Dynamic Social Networks: A Random Walk Approach

This study aims to tackling community detection problems in dynamic social networks. The main approach focuses on exploring the idea of random walk in formulating modularity functions for community detection. Under this approach, a modularity function is defined as the difference between the probability of a Markov chain induced by a community and the probability of a null model that assumes no detectable community structure exists in the network. In this paper, we demonstrate the modularity-based approach by applying it to identify group boundaries in an adolescence friendship networks spanning a period of five months. Results and future directions will be discussed.