Group Evolution Discovery in Social Networks

Abstract

Group extraction and their evolution are among the topics which arouse the greatest interest in the domain of social network analysis. However, while the grouping methods in social networks are developed very dynamically, the methods of group evolution discovery and analysis are still uncharted territory on the social network analysis map. Therefore the new method for the group evolution discovery called GED is proposed in this paper. Additionally, the results of the first experiments on the email based social network together with comparison with two other methods of group evolution discovery are presented.Comment: Brodka, P.; Saganowski, S.; Kazienko, P., "Group Evolution Discovery in Social Networks," Advances in Social Networks Analysis and Mining (ASONAM), 2011 International Conference on, vol., no., pp.247,253, 25-27 July 2011 doi: 10.1109/ASONAM.2011.6

A Diffusion Mechanism over Interest-based Communities in Mobile Internet

“…They have revealed that link creation is driven by proximity, triangle closure, reciprocation and homophily [5]- [11]. Recently, findings from social network analysis have been corroborated and expanded by the study of communication networks [2].…”

Core-Based Dynamic Community Detection in Mobile Social Networks

“…Nodes are usually depicted as people in the real world, and links are denoted to the contacts among nodes. The static approaches focus on high aggregation of nodes which have same features [1,2], while the dynamic approaches divide the network's evolving process into a few of timestamps, not only paying attention to the degree of aggregation, but also to the computational complexity at each timestamp [3,4]. However, few of these methods consider the stability of communities between two timestamps.…”

“…Researchers [3,7] have classified all of the situations that occur at each timestamp into several events, including node addition/removal and link addition/removal. Their experiment results demonstrate that discretization of the continuous time is a useful way to model the evolution of a network.…”

“…Besides these algorithms concerned with the evolution procedures of communities, community detection in dynamic social networks aims to detect the optimal community partition at each timestamp [4,7,[17][18][19]. Moreover, in order to describe the change of communities at different timestamps, tracking algorithms [20,21] based on similarity comparison have also been studied.…”

“…In previous literatures a broad consensus on the basic events that can be used to describe the evolution of dynamic communities can be seen [3,7,24]. We extend and specify these events-based cumulative stable contacts as follows ( Figure 7): Birth: There is a cumulative stable contact between two nodes, and the nodes belong to no communities before.…”