Machine Learning Approaches for Community Detection in Online Social Networks

Aurélio Ribeiro Costa, Rafael Henrique Nogalha de Lima, Célia Ghedini Ralha

Abstract: Network analysis is responsible for taking insights or generating predictions from networked data sources where community detection finds chunks of related data in a network. The importance of community detection spans in different domain applications, from social network formation to protein interaction predictions. This work compares five state-of-the-art solutions to community detection using machine learning approaches in the context of online social networks - Graph-GAN, SDNE, ComE, AC2CD, and CLARE. The experiments using real-world online social network datasets (Email-EU-Core, BlogCatalog3, Flickr) with micro-F1, macro-F1, and NMI scores demonstrate that graph neural networks and deep reinforcement learning approaches are better suited for the community detection task than others based on probabilistic or shallow networks.