Group detection can defined as the clustering of nodes in a graph into groups or communities. This may be a hard partitioning of the nodes, or may allow for overlapping group memberships. A community can be defined as a group of nodes that share dense connections among each other, while being less tightly connected to nodes in different communities in the network. The importance of communities lies in the fact that they can often be closely related to modular units in the system that have a common function, e.g., groups of individuals interacting with each other in a society (Girvan & Newman, 2002), WWW pages related to similar topics (Flake, Lawrence, Giles, & Coetzee, 2002), or proteins having the same biological function within the cell (Chen & Yuan, 2006).
Motivation and Background
The work done in group detection goes back as early as the 1920s when Stuart Rice clustered data by hand to investigate...
- Flake, G. W., Lawrence, S., Giles, C. L., & Coetzee, F. (2002). Self-organization and identification of web communities. IEEE Computer, 35, 66–71.Google Scholar
- Homans, G. C. (1950). The human group. New York: Harcourt, Brace.Google Scholar
- MacQueen, J. B. (1967). Some methods for classification and analysis of multivariate observations. In Proceedings of fifth Berkeley symposium on mathematical statistics and probability (Vol. 1, pp. 281–297). Berkeley, CA: University of California Press.Google Scholar
- Shalizi, C. R., Camperi, M. F., & Klinkner, K. L. (2007). Discovering functional communities in dynamical networks. Statistical network analysis: Models, issues, and new directions (pp. 140–157). Berlin: Springer-Verlag.Google Scholar
- Tantipathananandh, C., & Berger-Wolf, T. Y. (2009). Algorithms for identifying dynamic communities. In Proceedings of the 15th ACM SIGKDD international conference on knowledge discovery and data mining, Paris. New York: ACM.Google Scholar