In recent years, community detection has received increased attention thanks to its wide range of applications in many fields. While at first most techniques were focused on discovering communities in static networks, lately the research community’s focus has shifted toward methods that can detect meaningful substructures in evolving networks because of their high relevance in real-life problems. This thesis explores the current availability of empirical comparative studies of dynamic methods and also provides its own qualitative and quantitative comparison with the aim of gaining more insight in the performance of available algorithms that are expected to perform well in the context of social community detection. The qualitative comparison includes 13 algorithms, namely D-GT, Extended BGL, TILES, AFOCS, HOCTracker, OLCPM, DOCET, LabelRankT, FacetNet, DYNMOGA, DEMON and iLCD. The empirical analysis compares TILES, HOCTracker, OLCPM, DEMON and iLCD on synthetic RDyn graphs and the real graph, DBLP. In addition to the results of the empirical and qualitative results of the analysis, the thesis’s value lies in its wide coverage of the dynamic community detection problem.
