The earliest published work i found about the phases of community evolution belong to Toyoda and Kitsuregawa from University of Tokyo. They differentiate between phases of community evolution: emerge, dissolve, grow and shrink, split, and merge. They use Japanese web archives to prove their rules for each of the evolution phase. They use an extension of HITS to detect communities.
Later Palla and colleagues present their seminal work with beautiful visualization of different phases that i will add here.
Greene et al. and Gliwa et al. play with same or similar phases using Jaccard Index to define the changes that indicate the move of a community from one phase to the other.
Other research directions investigate community evolution and find feature sets that predict length of community life and its growth [1-5].
But some facts about community evolution still stays unclear: 1) how can one characterize the stages of community life-cycles? 2) what are the changes of community content during its evolution?
Later i will post some results of my research work that answer these questions.
1. L. Backstrom, D. Huttenlocher, J. Kleinberg, and X. Lan. Group formation in large social networks. In
the 12th ACM SIGKDD international conference, pages 44-54, New York and NY and USA, 2006. ACM.
2. S. R. Kairam, D. J. Wang, and J. Leskovec. The life and death of online groups: predicting group growth
and longevity. In the Fifth ACM international conference on Web search and data mining, pages
673-682, 2012.
3. M. K. Goldberg, M. Magdon-Ismail, and J. Thompson. Identifying Long Lived Social Communities Using
Structural Properties. In IEEE/ACM International Conference on Advances in Social Networks Analysis
and Mining (ASONAM), pages 647-653, 2012.
4. A. Patil, J. Liu, and J. Gao. Predicting Group Stability in Online Social Networks. In Proceedings of
the 22nd International Conference on World Wide Web, WWW '13, pages 1021{1030, Republic and
Canton of Geneva and Switzerland, 2013. International World Wide Web Conferences Steering Committee.
5. E. Zheleva, H. Sharara, and L. Getoor. Co-evolution of social and a liation networks. In Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining, KDD '09, pages 1007-1016, New York and NY and USA, 2009. ACM.
Later Palla and colleagues present their seminal work with beautiful visualization of different phases that i will add here.
Other research directions investigate community evolution and find feature sets that predict length of community life and its growth [1-5].
But some facts about community evolution still stays unclear: 1) how can one characterize the stages of community life-cycles? 2) what are the changes of community content during its evolution?
Later i will post some results of my research work that answer these questions.
1. L. Backstrom, D. Huttenlocher, J. Kleinberg, and X. Lan. Group formation in large social networks. In
the 12th ACM SIGKDD international conference, pages 44-54, New York and NY and USA, 2006. ACM.
2. S. R. Kairam, D. J. Wang, and J. Leskovec. The life and death of online groups: predicting group growth
and longevity. In the Fifth ACM international conference on Web search and data mining, pages
673-682, 2012.
3. M. K. Goldberg, M. Magdon-Ismail, and J. Thompson. Identifying Long Lived Social Communities Using
Structural Properties. In IEEE/ACM International Conference on Advances in Social Networks Analysis
and Mining (ASONAM), pages 647-653, 2012.
4. A. Patil, J. Liu, and J. Gao. Predicting Group Stability in Online Social Networks. In Proceedings of
the 22nd International Conference on World Wide Web, WWW '13, pages 1021{1030, Republic and
Canton of Geneva and Switzerland, 2013. International World Wide Web Conferences Steering Committee.
5. E. Zheleva, H. Sharara, and L. Getoor. Co-evolution of social and a liation networks. In Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining, KDD '09, pages 1007-1016, New York and NY and USA, 2009. ACM.
