@electronic{plg1.cs.uwaterloo.ca, title = {Spam Dataset Trec}, url = {http://plg1.cs.uwaterloo.ca/cgi-bin/cgiwrap/gvcormac/foo07}, biburl = {https://puma.uni-kassel.de/url/c61a7a3ad2a1ff12a3967a73a6648972/hotho}, keywords = {dataset spam trec}, added-at = {2010-08-16T14:03:26.000+0200}, description = {}, interhash = {c61a7a3ad2a1ff12a3967a73a6648972}, intrahash = {c61a7a3ad2a1ff12a3967a73a6648972} } @electronic{www.technologyreview.com, title = {Technology Review: A Better Way to Rank Expertise Online}, url = {http://www.technologyreview.com/web/23100/}, biburl = {https://puma.uni-kassel.de/url/17bcfb86c4035b5b7cdd1623360a73ca/hotho}, keywords = {bookmarking detection social spam}, added-at = {2009-07-31T18:05:09.000+0200}, description = {}, interhash = {17bcfb86c4035b5b7cdd1623360a73ca}, intrahash = {17bcfb86c4035b5b7cdd1623360a73ca} } @electronic{givealink.org, title = {Social Spam Detection Benjamin Markines Ciro Cattuto Filippo Menczer}, url = {http://givealink.org/Site/socialspam.html}, biburl = {https://puma.uni-kassel.de/url/5c0a079043ca59026f82d178ffa4e4e6/hotho}, keywords = {detection dataset classification bibsonomy spam}, added-at = {2009-04-01T17:04:55.000+0200}, description = {Social Spam Detection}, interhash = {5c0a079043ca59026f82d178ffa4e4e6}, intrahash = {5c0a079043ca59026f82d178ffa4e4e6} } @electronic{heymann.stanford.edu, title = {Tag Spam}, url = {http://heymann.stanford.edu/tagspam.html}, biburl = {https://puma.uni-kassel.de/url/22399620dafee1777649682e11f83ee3/hotho}, keywords = {? folksonomy model spam tagging}, added-at = {2009-02-20T16:24:01.000+0100}, description = {}, interhash = {22399620dafee1777649682e11f83ee3}, intrahash = {22399620dafee1777649682e11f83ee3} } @electronic{www.yr-bcn.es, title = {Datasets}, url = {http://www.yr-bcn.es/webspam/datasets/}, biburl = {https://puma.uni-kassel.de/url/738cfa05f2740cb277561053597f68e4/hotho}, keywords = {dataset detection spam webspam}, added-at = {2007-07-19T01:15:17.000+0200}, description = {}, interhash = {738cfa05f2740cb277561053597f68e4}, intrahash = {738cfa05f2740cb277561053597f68e4} } @electronic{recaptcha.net, title = {reCAPTCHA: Stop Spam, Read Books}, url = {http://recaptcha.net/}, biburl = {https://puma.uni-kassel.de/url/720bff062ad558c506ab94167ae9477f/hotho}, keywords = {capture service spam stop web}, added-at = {2007-07-17T17:45:25.000+0200}, description = {}, interhash = {720bff062ad558c506ab94167ae9477f}, intrahash = {720bff062ad558c506ab94167ae9477f} } @electronic{www.ecmlpkdd2006.org, title = {ECML/PKDD Discovery Challenge 2006}, url = {http://www.ecmlpkdd2006.org/challenge.html}, biburl = {https://puma.uni-kassel.de/url/1564dc028dc534329f5e50e18d625fba/hotho}, keywords = {KI2007WebMining dataset detection email spam}, added-at = {2007-05-18T20:38:05.000+0200}, description = {}, interhash = {1564dc028dc534329f5e50e18d625fba}, intrahash = {1564dc028dc534329f5e50e18d625fba} } @electronic{www.greylisting.org, title = {Greylisting.org - Postfix implementations}, url = {http://www.greylisting.org/implementations/postfix.shtml}, biburl = {https://puma.uni-kassel.de/url/be7476f177266c29056c3a1e4c367b4b/hotho}, keywords = {greylisting mail postfix spam}, added-at = {2007-03-27T09:20:53.000+0200}, description = {Postfix now includes the sample greylisting policy-daemon in the main release (2.1+): www.postfix.org/SMTPD_POLICY_README.html#greylist.}, interhash = {be7476f177266c29056c3a1e4c367b4b}, intrahash = {be7476f177266c29056c3a1e4c367b4b} } @electronic{webspam.lip6.fr, title = {Web Spam Challenge - HomePage}, url = {http://webspam.lip6.fr/wiki/pmwiki.php}, biburl = {https://puma.uni-kassel.de/url/9a3be357cb77d5ed78fbe37d563f8b36/hotho}, keywords = {web spam detection 2007 challenge workshop}, added-at = {2007-01-23T14:04:04.000+0100}, description = {}, interhash = {9a3be357cb77d5ed78fbe37d563f8b36}, intrahash = {9a3be357cb77d5ed78fbe37d563f8b36} } @electronic{www.youbookmark.com, title = {YouBookmark: Store, share and tag your favourite links}, url = {http://www.youbookmark.com/}, biburl = {https://puma.uni-kassel.de/url/6dad6915233e300e364aa9448ea9197b/hotho}, keywords = {folksonomy spam tools}, added-at = {2006-12-21T12:13:18.000+0100}, description = {}, interhash = {6dad6915233e300e364aa9448ea9197b}, intrahash = {6dad6915233e300e364aa9448ea9197b} } @electronic{plg.uwaterloo.ca, title = {Trec Spam Corpus}, url = {http://plg.uwaterloo.ca/~gvcormac/treccorpus/}, biburl = {https://puma.uni-kassel.de/url/612bf65a435736bdb79b895c6b070429/hotho}, keywords = {trec spam set data dataset corpus}, added-at = {2006-09-04T15:42:51.000+0200}, description = {}, interhash = {612bf65a435736bdb79b895c6b070429}, intrahash = {612bf65a435736bdb79b895c6b070429} } @electronic{trac.edgewall.org, title = {SpamFilter - The Trac Project - Trac}, url = {http://trac.edgewall.org/wiki/SpamFilter}, biburl = {https://puma.uni-kassel.de/url/9f66462073fabd53bb25b28adeacb878/hotho}, keywords = {filter spam wiki}, added-at = {2006-07-19T14:12:08.000+0200}, description = {}, interhash = {9f66462073fabd53bb25b28adeacb878}, intrahash = {9f66462073fabd53bb25b28adeacb878} } @electronic{blogoforum.com, title = {del.icio.us spammed with automated tool | blog+forum on antispam, del.icio.us, spam, news | blogoforum}, url = {http://blogoforum.com/tag/antispam+del.icio.us+news+spam/del-icio-us-spammed-with-automated-tool-2216.html}, biburl = {https://puma.uni-kassel.de/url/5fac6b5e789a24e0b353438affeed6a2/hotho}, keywords = {folksonomy spam tor del.icio.us}, added-at = {2006-07-10T19:45:27.000+0200}, description = {}, interhash = {5fac6b5e789a24e0b353438affeed6a2}, intrahash = {5fac6b5e789a24e0b353438affeed6a2} } @electronic{plg.uwaterloo.ca, title = {Batch and Online Spam Filter Comparison}, url = {http://plg.uwaterloo.ca/~gvcormac/ceas06.pdf}, biburl = {https://puma.uni-kassel.de/url/d998db660d2d88659f4d5a9689b33b6d/hotho}, keywords = {drift spam classification concept}, added-at = {2006-06-24T12:28:56.000+0200}, description = {}, interhash = {d998db660d2d88659f4d5a9689b33b6d}, intrahash = {d998db660d2d88659f4d5a9689b33b6d} } @electronic{www.vldb.org, title = {Combating Web Spam with TrustRank}, url = {http://www.vldb.org/conf/2004/RS15P3.PDF}, biburl = {https://puma.uni-kassel.de/url/1fd9e52c8bcf628ee02b5aeee6d4f935/hotho}, keywords = {web search social spam rank trust network}, added-at = {2006-02-13T08:09:11.000+0100}, description = {Web spam pages use various techniques to achieve higher-than-deserved rankings in a search engine’s results. While human experts can identify spam, it is too expensive to manually evaluate a large number of pages. Instead, we propose techniques to semi-automatically separate reputable, good pages from spam. We first select a small set of seed pages to be evaluated by an expert. Once we manually identify the reputable seed pages, we use the link structure of the web to discover other pages that are likely to be good. In this paper we discuss possible ways to implement the seed selection and the discovery of good pages. We present results of experiments run on the World Wide Web indexed by AltaVista and evaluate the performance of our techniques. Our results show that we can effectively filter out spam from a significant fraction of the web, based on a good seed set of less than 200 sites.}, interhash = {1fd9e52c8bcf628ee02b5aeee6d4f935}, intrahash = {1fd9e52c8bcf628ee02b5aeee6d4f935} } @electronic{www.mailinator.com, title = {Mailinator:Home}, url = {http://www.mailinator.com/mailinator/index.jsp}, biburl = {https://puma.uni-kassel.de/url/bbe216e5d91b68ce38531929043b38f0/hotho}, keywords = {spam temporary address email antispam}, added-at = {2006-01-17T18:31:01.000+0100}, description = {}, interhash = {bbe216e5d91b68ce38531929043b38f0}, intrahash = {bbe216e5d91b68ce38531929043b38f0} }