***** To join INSNA, visit http://www.insna.org *****
My method called SCAN and extension DISSECT can be used for identifying communities using cohesive subgroups, centrality and similarity.
Chin A, Chignell M (2008) Automatic detection of cohesive subgroups within social hypertext: A heuristic approach. New Review of Hypermedia and Multimedia 14(1):121–143
Chin, A., Chignell, M. DISSECT: Data-Intensive Socially Similar Evolving Community Tracker. In Computational Social Network Analysis: Trends, Tools, and Research Advances (Ed. Ajith Abraham, Aboul-Ella Hassanien, and Vaclav Snasel), London: Springer-Verlag London Limited, 2010, 81-106.
***** To join INSNA, visit http://www.insna.org *****Thanks to Jim for mentioning our methodology for identifying communities across multiple times (and/or multiple scales, types of connections). The reference is
Mucha, Peter J, Thomas Richardson, Kevin Macon, Mason A. Porter, and Jukka-Pekka Onnela. 2009. Community Structure in Time-Dependent, Multiscale, and Multiplex Networks. submitted. http://arxiv.org/abs/0911.1824.
This is of course not the only way to study communities in dynamic data---see the reviews previously mentioned in this thread---but it has the property of being intimately related to the existing modularity methodologies for community detection, which is IMHO nice for many circumstances.
Peter J. Mucha, Associate Professor
Department of Mathematics
Carolina Center for Interdisciplinary Applied Mathematics
Institute for Advanced Materials, Nanoscience and Technology
The University of North Carolina at Chapel Hill
Campus Box #3250, UNC, Chapel Hill, NC 27599-3250
Phone: 919/843-2550, Fax: 919/962-9345, Office: 304B Phillips Hall
[log in to unmask], http://www.unc.edu/~mucha
SOCNET is a service of INSNA, the professional association for social
network researchers (http://www.insna.org). To unsubscribe, send
an email message to [log in to unmask] containing the line
UNSUBSCRIBE SOCNET in the body of the message.