Finding Communities in Dynamic Social Networks.pdfVIP

2011 11th IEEE International Conference on Data Mining Finding Communities in Dynamic Social Networks Chayant Tantipathananandh and Tanya Y. Berger-Wolf Department of Computer Science University of Illinois at Chicago 851 S Morgan St Chicago, IL 60607 Email: {ctanr ti2, tanyabvv}@ Abstract—Communities are natural structures observed in consider the temporal aspect of the system of interactions. social networks and are usually characterized as “relatively We call such a system of interactions a “dynamic network” dense” subsets of nodes. Social networks change over time as opposed to a “static network.” and so do the underlying community structures. Thus, to truly uncover this structure we must take the temporal aspect of Recently, researchers have proposed many methods for networks into consideration. Previously, we have represented identifying dynamic communities [5]. All such methods rely framework for finding dynamic communities using the social on the notion of gradual change of community membership cost model and formulated the corresponding optimization and some notion of persistence [2]. This line of research problem [33], assuming that partitions of individuals into groups began with several methods that track, rather than infer, are given in each time step. We have also presented heuristics and approximation algorithms