{"id":"https://openalex.org/W2129487958","doi":"https://doi.org/10.1145/1244408.1244411","title":"Improving web spam classification using rank-time features","display_name":"Improving web spam classification using rank-time features","publication_year":2007,"publication_date":"2007-05-08","ids":{"openalex":"https://openalex.org/W2129487958","doi":"https://doi.org/10.1145/1244408.1244411","mag":"2129487958"},"language":"en","primary_location":{"id":"doi:10.1145/1244408.1244411","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1244408.1244411","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd international workshop on Adversarial information retrieval on the web","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019716296","display_name":"Krysta M. Svore","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Krysta M. Svore","raw_affiliation_strings":["Microsoft Research, Redmond, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063629854","display_name":"Qiang Wu","orcid":"https://orcid.org/0000-0001-5641-2483"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qiang Wu","raw_affiliation_strings":["Microsoft Research, Redmond, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069708056","display_name":"Chris Burges","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chris J. C. Burges","raw_affiliation_strings":["Microsoft Research, Redmond, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089342501","display_name":"Aaswath P. Raman","orcid":"https://orcid.org/0000-0003-0106-8341"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aaswath Raman","raw_affiliation_strings":["Microsoft Redmond, WA","Microsoft, Redmond, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":2.6177,"has_fulltext":false,"cited_by_count":45,"citation_normalized_percentile":{"value":0.91022906,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"9","last_page":"16"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8267993927001953},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6941742897033691},{"id":"https://openalex.org/keywords/spamdexing","display_name":"Spamdexing","score":0.6658420562744141},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.5394793748855591},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.5336588025093079},{"id":"https://openalex.org/keywords/learning-to-rank","display_name":"Learning to rank","score":0.5059079527854919},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4969938099384308},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.4836362600326538},{"id":"https://openalex.org/keywords/web-query-classification","display_name":"Web query classification","score":0.46812358498573303},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46367478370666504},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.44697368144989014},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4376629590988159},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.2567189931869507},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.2140735387802124},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.20317959785461426},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.09584182500839233},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08114299178123474}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8267993927001953},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6941742897033691},{"id":"https://openalex.org/C13565553","wikidata":"https://www.wikidata.org/wiki/Q804206","display_name":"Spamdexing","level":5,"score":0.6658420562744141},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.5394793748855591},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.5336588025093079},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.5059079527854919},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4969938099384308},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.4836362600326538},{"id":"https://openalex.org/C118689300","wikidata":"https://www.wikidata.org/wiki/Q7978614","display_name":"Web query classification","level":4,"score":0.46812358498573303},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46367478370666504},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.44697368144989014},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4376629590988159},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.2567189931869507},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.2140735387802124},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.20317959785461426},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.09584182500839233},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08114299178123474},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1244408.1244411","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1244408.1244411","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd international workshop on Adversarial information retrieval on the web","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.114.7083","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.114.7083","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www2007.org/workshops/paper_101.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W740415","https://openalex.org/W38924359","https://openalex.org/W252574719","https://openalex.org/W1529464143","https://openalex.org/W1987365175","https://openalex.org/W2050028965","https://openalex.org/W2066055909","https://openalex.org/W2073562093","https://openalex.org/W2108671511","https://openalex.org/W2120926619","https://openalex.org/W2139148100","https://openalex.org/W2143331230","https://openalex.org/W2156632103","https://openalex.org/W2156909104","https://openalex.org/W2169270715","https://openalex.org/W2401383085","https://openalex.org/W2597608265"],"related_works":["https://openalex.org/W2368945903","https://openalex.org/W4255972148","https://openalex.org/W2222022498","https://openalex.org/W2062919806","https://openalex.org/W3437724","https://openalex.org/W4312784821","https://openalex.org/W2922524414","https://openalex.org/W2227686825","https://openalex.org/W2078337952","https://openalex.org/W4379381520"],"abstract_inverted_index":{"In":[0,69,92],"this":[1,56],"paper,":[2],"we":[3,38,53,71,111],"study":[4],"the":[5,41,117,127,131,149],"classification":[6,51,95],"of":[7,43,119,133,151],"web":[8,89,121,143],"spam.":[9],"Web":[10],"spam":[11,50,90,122,144],"refers":[12],"to":[13,18,67,85,129,158],"pages":[14],"that":[15,40,55,73,148],"use":[16,132,150],"techniques":[17],"mislead":[19],"search":[20],"engines":[21],"into":[22],"assigning":[23],"them":[24],"higher":[25],"rank,":[26],"thus":[27],"increasing":[28],"their":[29],"site":[30],"traffic.":[31],"Our":[32,124],"contributions":[33],"are":[34],"two":[35],"fold.":[36],"First,":[37],"find":[39,72],"method":[42],"datset":[44],"construction":[45],"is":[46,83,126],"crucial":[47],"for":[48,142],"accurate":[49],"and":[52,63,80,136,153],"note":[54],"problem":[57],"occurs":[58],"generally":[59],"in":[60,104,137,161],"learning":[61],"problems":[62],"can":[64,97,115,156],"be":[65],"hard":[66],"detect.":[68],"particular,":[70],"ensuring":[74],"no":[75],"overlapping":[76],"domains":[77],"between":[78],"test":[79,87],"training":[81],"sets":[82],"necessary":[84],"accurately":[86],"a":[88,120,164],"classifier.":[91,123],"our":[93],"case,":[94],"performance":[96,118],"differ":[98],"by":[99],"as":[100,102],"much":[101],"40%":[103],"precision":[105],"when":[106],"using":[107,167],"non-domain-separated":[108],"data.":[109],"Second,":[110],"show":[112,147],"rank-time":[113,134,140,152],"features":[114,155],"improve":[116],"paper":[125],"first":[128],"investigate":[130],"features,":[135,141],"particular":[138],"query-dependent":[139,154],"detection.":[145],"We":[146],"lead":[157],"an":[159],"increase":[160],"accuracy":[162],"over":[163],"classifier":[165],"trained":[166],"page-based":[168],"content":[169],"only.":[170]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":13}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}