We define a community on the web as a set of sites that have more links (in either direction) to members of the community than to non-members. Members of such a community can be efficiently identified in a maximum flow / minimum cut framework, where the source is composed of known members, and the sink consists of well-known non-members. A focused crawler that crawls to a fixed depth can approximate community membership by augmenting the graph induced by the crawl with links to a virtual sink...
%0 Conference Proceedings
%1 citeulike:3128
%A Flake, Gary
%A Lawrence, Steve
%A Giles, Lee L.
%B Sixth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
%C Boston, MA
%D 2000
%K clustering max_flow web web_graph community
%P 150--160
%T Efficient Identification of Web Communities
%U http://citeseer.ist.psu.edu/flake00efficient.html
%X We define a community on the web as a set of sites that have more links (in either direction) to members of the community than to non-members. Members of such a community can be efficiently identified in a maximum flow / minimum cut framework, where the source is composed of known members, and the sink consists of well-known non-members. A focused crawler that crawls to a fixed depth can approximate community membership by augmenting the graph induced by the crawl with links to a virtual sink...
@proceedings{citeulike:3128,
abstract = {We define a community on the web as a set of sites that have more links (in either direction) to members of the community than to non-members. Members of such a community can be efficiently identified in a maximum flow / minimum cut framework, where the source is composed of known members, and the sink consists of well-known non-members. A focused crawler that crawls to a fixed depth can approximate community membership by augmenting the graph induced by the crawl with links to a virtual sink...},
added-at = {2006-09-04T15:49:50.000+0200},
address = {Boston, MA},
author = {Flake, Gary and Lawrence, Steve and Giles, Lee L.},
biburl = {https://www.bibsonomy.org/bibtex/237985f2c54c08d5db2a28a24735bd9aa/hotho},
booktitle = {Sixth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining},
citeulike-article-id = {3128},
interhash = {fe87690693bc84a663c00371684da561},
intrahash = {37985f2c54c08d5db2a28a24735bd9aa},
keywords = {clustering max_flow web web_graph community},
month = {August February0--FebruaryMarch},
pages = {150--160},
timestamp = {2006-09-04T15:49:50.000+0200},
title = {Efficient Identification of Web Communities},
url = {http://citeseer.ist.psu.edu/flake00efficient.html},
year = 2000
}