Direct Comparative Analysis of Nature-inspired Optimization Algorithms on Community Detection Problem in Social Networks

TL;DR

This paper compares the performance of four nature-inspired optimization algorithms in community detection tasks within social networks, using real-world data and multiple evaluation metrics to identify the most effective approaches.

Contribution

It provides a direct comparative analysis of NIOAs for community detection, highlighting their relative effectiveness on real social network data.

Findings

NIOAs vary significantly in community detection quality.

Performance metrics based on prasatul matrix and isolability are effective.

Some algorithms outperform others consistently across datasets.

Abstract

Nature-inspired optimization Algorithms (NIOAs) are nowadays a popular choice for community detection in social networks. Community detection problem in social network is treated as optimization problem, where the objective is to either maximize the connection within the community or minimize connections between the communities. To apply NIOAs, either of the two, or both objectives are explored. Since NIOAs mostly exploit randomness in their strategies, it is necessary to analyze their performance for specific applications. In this paper, NIOAs are analyzed on the community detection problem. A direct comparison approach is followed to perform pairwise comparison of NIOAs. The performance is measured in terms of five scores designed based on prasatul matrix and also with average isolability. Three widely used real-world social networks and four NIOAs are considered for analyzing the quality of communities generated by NIOAs.