Analysis of Spectral clustering approach for tracking community formation in social network

Abstract

The study of tracking community formation in social networks is an active area of research. A common pattern among the cohesive subgroup of people in a network is considered as a community which is a partition of the entire network structure. In recent years, spectral clustering has become one of the most popular modern clustering algorithms. It is simple to implement, can be solved efficiently by standard linear algebra method and very often outperforms traditional clustering algorithms such as the k-means algorithm. Existing method of community tracking methods is based on hierarchical clustering algorithm. This paper establishes that spectral clustering is an efficient way for tracking community formation in social network.