Analysis of Communities of Interest in Data Networks

作者: William Aiello , Charles Kalmanek , Patrick McDaniel , Subhabrata Sen , Oliver Spatscheck

DOI: 10.1007/978-3-540-31966-5_7

关键词:

摘要: Communities of interest (COI) have been applied in a variety environments ranging from characterizing the online buying behavior individuals to detecting fraud telephone networks. The common thread among these applications is that historical COI an individual can be used predict future as well other members COI. It would clearly beneficial if COIs same manner characterize and hosts within data network. In this paper, we introduce methodology for evaluating various aspects IP context study, broadly define collection interacting hosts. We apply our using collected large enterprise network over eleven week period. First, study distributions stability size COIs. Second, evaluate multiple heuristics determine stable core set sets time. Third, how much communication not captured by sets.

参考文章(7)
Jon M. Kleinberg, Navigation in a small world Nature. ,vol. 406, pp. 845- 845 ,(2000) , 10.1038/35022643
John Guttag, Godfrey Tan, Frans Kaashoek, Massimiliano Poletto, Role classification of hosts within enterprise networks based on connection patterns usenix annual technical conference. pp. 2- 2 ,(2003)
Corinna Cortes, Daryl Pregibon, Chris Volinsky, Communities of Interest intelligent data analysis. ,vol. 6, pp. 105- 114 ,(2001) , 10.1007/3-540-44816-0_11
R. Kumar, P. Ragbavan, S. Rajagopalan, A. Tomkins, The Web and social networks IEEE Computer. ,vol. 35, pp. 32- 36 ,(2002) , 10.1109/MC.2002.1046971
Emily M. Jin, Michelle Girvan, M. E. J. Newman, Structure of growing social networks. Physical Review E. ,vol. 64, pp. 046132- 046132 ,(2001) , 10.1103/PHYSREVE.64.046132
Jon Kleinberg, The small-world phenomenon: an algorithmic perspective symposium on the theory of computing. pp. 163- 170 ,(2000) , 10.1145/335305.335325
Chuck Cranor, Theodore Johnson, Oliver Spataschek, Vladislav Shkapenyuk, Gigascope: a stream database for network applications international conference on management of data. pp. 647- 651 ,(2003) , 10.1145/872757.872838