Social significance of community structure: Statistical view

TL;DR

This paper introduces a statistical framework for evaluating the significance of community structures in social networks, accounting for real-world complexities like randomness and errors, and applies it to both benchmark and real social data.

Contribution

It presents a novel method combining social hierarchy modeling, similarity measures, and p-value based significance testing for community analysis.

Findings

Effective in determining the optimal number of communities

Able to assess the social significance of communities

Useful for comparing different community detection algorithms

Abstract

Community structure analysis is a powerful tool for social networks, which can simplify their topological and functional analysis considerably. However, since community detection methods have random factors and real social networks obtained from complex systems always contain error edges, evaluating the significance of community structure partitioned is an urgent and important question. In this paper, integrating the specific characteristics of real society, we present a novel framework analyzing the significance of social community specially. The dynamics of social interactions are modeled by identifying social leaders and corresponding hierarchical structures. Instead of a direct comparison with the average outcome of a random model, we compute the similarity of a given node with the leader by the number of common neighbors. To determine the membership vector, an efficient community detection algorithm is proposed based on the position of nodes and their corresponding leaders. Then, using log-likelihood score, the tightness of community can be derived. Based on the distribution of community tightness, we establish a new connection between $p$-value theory and network analysis and then get a novel statistical form significance measure. Finally, the framework is applied to both benchmark networks and real social networks. Experimental results show that our work can be used in many fields, such as determining the optimal number of communities, analyzing the social significance of a given community, comparing the performance among various algorithms and so on.