Community dynamics mining

In this paper we propose a model to analyze community dynamics. Recently, several methods and tools have been proposed to extract communities from static graphs. However, since communities are not static, but change over time, it is necessary to provide methods to determine and observe the community transitions and to extract the factors that cause the development. We regard a community as an object that exists over time and propose to observe community transitions along the time axis. For this we partition the time axis under observation by time windows. In each time window, a set of interactions between community participants is aggregated. These static networks are analyzed for subcommunities by applying community detection mechanisms. Through this we detect communities in each interval and can observe if communities persist over time or undergo a transition. We present community transitions and the observable indicators for the respective development. We furthermore present a software environment that incorporates several community detection and analysis methods to analyze community transitions. It supports a dynamic temporal community analysis and provides several forms of visualizations and analysis settings thus providing an interactive tool to observe community dynamics.