Quantcast

Towards the Dynamic Community Discovery in Decentralized Online Social Networks

Research paper by Barbara Guidi, Andrea Michienzi; Giulio Rossetti

Indexed on: 14 Jul '18Published on: 12 Jul '18Published in: Journal of Grid Computing



Abstract

The community structure is one of the most studied features of the Online Social Networks (OSNs). Community detection guarantees several advantages for both centralized and decentralized social networks. Decentralized Online Social Networks (DOSNs) have been proposed to provide more control over private data. Several challenges in DOSNs can be faced by exploiting communities. The detection of communities and the management of their evolution represents a hard process, especially in highly dynamic environments, where churn is a real problem. In this paper, we focus our attention on the analysis of dynamic community detection in DOSNs by studying a real Facebook dataset. We evaluate two different dynamic community discovery classes to understand which of them can be applied to a distributed environment. Results prove that the social graph has high instability and distributed solutions to manage the dynamism are needed and show that a Temporal Trade-off class is the most promising one.