Published Paper Details:

Community detection is a vital task in the analysis of social networks, where the goal is to identify groups of nodes that are highly interconnected and exhibit similar characteristics. This problem has received significant attention due to its wide range of applications in various fields, such as marketing, recommendation systems, and sociology. In recent years, numerous algorithms have been proposed to solve this problem, ranging from traditional clustering techniques to modern deep learning-based methods. In this paper we experiment with several algorithms to find overlapping and disjoint communities. Louvain and Label propagation algorithms are used to detect overlapping communities. Girvan-Newman and K-clique are used to detect the disjoint communities. A Graph Neural Network (GNN) is a type of neural network designed to operate on graph-structured data, which is a collection of nodes and edges that represent relationships between them. A GNN based community detection is also carried out and compared with existing methods.