{"id":"https://openalex.org/W2099324655","doi":"https://doi.org/10.1145/1135777.1135793","title":"Site level noise removal for search engines","display_name":"Site level noise removal for search engines","publication_year":2006,"publication_date":"2006-05-23","ids":{"openalex":"https://openalex.org/W2099324655","doi":"https://doi.org/10.1145/1135777.1135793","mag":"2099324655"},"language":"en","primary_location":{"id":"doi:10.1145/1135777.1135793","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1135777.1135793","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th international conference on World Wide Web","raw_type":"proceedings-article"},"type":"article","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/A5103678083","display_name":"Andr\u00e9 Luiz da Costa Carvalho","orcid":null},"institutions":[{"id":"https://openalex.org/I62885914","display_name":"Universidade Federal do Amazonas","ror":"https://ror.org/02263ky35","country_code":"BR","type":"education","lineage":["https://openalex.org/I62885914"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Andr\u00e9 Luiz da Costa Carvalho","raw_affiliation_strings":["Federal University of Amazonas, Ramos, Manaus, Brazil"],"affiliations":[{"raw_affiliation_string":"Federal University of Amazonas, Ramos, Manaus, Brazil","institution_ids":["https://openalex.org/I62885914"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111849640","display_name":"Paul - Alexandru Chirita","orcid":null},"institutions":[{"id":"https://openalex.org/I114112103","display_name":"Leibniz University Hannover","ror":"https://ror.org/0304hq317","country_code":"DE","type":"education","lineage":["https://openalex.org/I114112103"]},{"id":"https://openalex.org/I4210136150","display_name":"L3S Research Center","ror":"https://ror.org/039t4wk02","country_code":"DE","type":"facility","lineage":["https://openalex.org/I114112103","https://openalex.org/I4210136150","https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Paul - Alexandru Chirita","raw_affiliation_strings":["L3S and University of Hannover, Hannover, Germany","L3S and University of Hannover, Hannover, Germany#TAB#"],"affiliations":[{"raw_affiliation_string":"L3S and University of Hannover, Hannover, Germany","institution_ids":["https://openalex.org/I4210136150"]},{"raw_affiliation_string":"L3S and University of Hannover, Hannover, Germany#TAB#","institution_ids":["https://openalex.org/I114112103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015781017","display_name":"Edleno Silva de Moura","orcid":"https://orcid.org/0000-0002-7860-9575"},"institutions":[{"id":"https://openalex.org/I62885914","display_name":"Universidade Federal do Amazonas","ror":"https://ror.org/02263ky35","country_code":"BR","type":"education","lineage":["https://openalex.org/I62885914"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Edleno Silva de Moura","raw_affiliation_strings":["Federal University of Amazonas, Ramos, Manaus, Brazil"],"affiliations":[{"raw_affiliation_string":"Federal University of Amazonas, Ramos, Manaus, Brazil","institution_ids":["https://openalex.org/I62885914"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011911239","display_name":"P\u00e1vel Calado","orcid":"https://orcid.org/0000-0001-6478-229X"},"institutions":[{"id":"https://openalex.org/I121345201","display_name":"Instituto de Engenharia de Sistemas e Computadores Investiga\u00e7\u00e3o e Desenvolvimento","ror":"https://ror.org/04mqy3p58","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I121345201","https://openalex.org/I4210125590"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"P\u00e1vel Calado","raw_affiliation_strings":["IST/INESC-ID, Porto Salvo, Portugal","IST/Inesc-ID, Porto Salvo, Portugal"],"affiliations":[{"raw_affiliation_string":"IST/INESC-ID, Porto Salvo, Portugal","institution_ids":["https://openalex.org/I121345201"]},{"raw_affiliation_string":"IST/Inesc-ID, Porto Salvo, Portugal","institution_ids":["https://openalex.org/I121345201"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074427964","display_name":"Wolfgang Nejdl","orcid":"https://orcid.org/0000-0003-3374-2193"},"institutions":[{"id":"https://openalex.org/I114112103","display_name":"Leibniz University Hannover","ror":"https://ror.org/0304hq317","country_code":"DE","type":"education","lineage":["https://openalex.org/I114112103"]},{"id":"https://openalex.org/I4210136150","display_name":"L3S Research Center","ror":"https://ror.org/039t4wk02","country_code":"DE","type":"facility","lineage":["https://openalex.org/I114112103","https://openalex.org/I4210136150","https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Wolfgang Nejdl","raw_affiliation_strings":["L3S and University of Hannover, Hannover, Germany","L3S and University of Hannover, Hannover, Germany#TAB#"],"affiliations":[{"raw_affiliation_string":"L3S and University of Hannover, Hannover, Germany","institution_ids":["https://openalex.org/I4210136150"]},{"raw_affiliation_string":"L3S and University of Hannover, Hannover, Germany#TAB#","institution_ids":["https://openalex.org/I114112103"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5103678083"],"corresponding_institution_ids":["https://openalex.org/I62885914"],"apc_list":null,"apc_paid":null,"fwci":23.2374,"has_fulltext":false,"cited_by_count":44,"citation_normalized_percentile":{"value":0.99290001,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"73","last_page":"82"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9994000196456909,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9994000196456909,"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9990000128746033,"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":0.5987743735313416},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5956531167030334},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1809181272983551}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5987743735313416},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5956531167030334},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1809181272983551},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1135777.1135793","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1135777.1135793","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th international conference on World Wide Web","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.60.1983","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.60.1983","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.l3s.de/~chirita/publications/carvalho06site.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W49362422","https://openalex.org/W202878612","https://openalex.org/W1506845741","https://openalex.org/W1529550554","https://openalex.org/W1660390307","https://openalex.org/W1764421085","https://openalex.org/W1845137714","https://openalex.org/W1854214752","https://openalex.org/W1987365175","https://openalex.org/W2026875114","https://openalex.org/W2043900215","https://openalex.org/W2050028965","https://openalex.org/W2052841581","https://openalex.org/W2079672501","https://openalex.org/W2085470508","https://openalex.org/W2087303323","https://openalex.org/W2089199911","https://openalex.org/W2100815879","https://openalex.org/W2108671511","https://openalex.org/W2133986984","https://openalex.org/W2138621811","https://openalex.org/W2139148100","https://openalex.org/W2151626491","https://openalex.org/W2152314154","https://openalex.org/W2152565070","https://openalex.org/W2156632103","https://openalex.org/W2169270715","https://openalex.org/W2398953749","https://openalex.org/W4240407914","https://openalex.org/W6608203075","https://openalex.org/W6630516739","https://openalex.org/W6637101025","https://openalex.org/W6639055396","https://openalex.org/W6683392976","https://openalex.org/W6712818525"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2130043461","https://openalex.org/W2530322880","https://openalex.org/W1596801655"],"abstract_inverted_index":{"The":[0],"currently":[1],"booming":[2],"search":[3,57,153],"engine":[4,154],"industry":[5],"has":[6,37],"determined":[7],"many":[8],"online":[9],"organizations":[10],"to":[11,13,20,24],"attempt":[12],"artificially":[14],"increase":[15,159],"their":[16,25],"ranking":[17],"in":[18,160],"order":[19],"attract":[21],"more":[22],"visitors":[23],"web":[26,36,75,142],"sites.":[27,143],"In":[28,59],"the":[29,32,35,51,74,109,114,147,151,161,164],"same":[30],"time,":[31],"growth":[33],"of":[34,92,103,113,150,163],"also":[38],"inherently":[39],"generated":[40],"several":[41],"navigational":[42],"hyperlink":[43],"structures":[44],"which":[45],"have":[46],"a":[47,100,156],"negative":[48],"impact":[49],"on":[50],"importance":[52],"measures":[53],"employed":[54],"by":[55,89],"current":[56],"engines.":[58],"this":[60],"paper":[61],"we":[62,98],"propose":[63],"and":[64,120],"evaluate":[65],"algorithms":[66],"for":[67],"identifying":[68],"all":[69],"these":[70],"noisy":[71,104],"links":[72],"over":[73],"graph,":[76],"may":[77],"them":[78],"be":[79],"spam":[80],"or":[81],"simple":[82],"relationships":[83],"between":[84,141],"real":[85],"world":[86],"entities":[87],"represented":[88],"sites,":[90],"replication":[91],"content,":[93],"etc.":[94],"Unlike":[95],"prior":[96],"work,":[97],"target":[99],"different":[101],"type":[102],"link":[105,139,148],"structures,":[106],"residing":[107],"at":[108],"site":[110,122,132],"level,":[111],"instead":[112],"page":[115],"level.":[116],"We":[117],"thus":[118],"investigate":[119],"annihilate":[121],"level":[123],"mutual":[124],"reinforcement":[125],"relationships,":[126],"abnormal":[127],"support":[128],"coming":[129],"from":[130],"one":[131],"towards":[133],"another,":[134],"as":[135,137],"well":[136],"complex":[138],"alliances":[140],"Our":[144],"experiments":[145],"with":[146],"database":[149],"TodoBR":[152],"show":[155],"very":[157],"strong":[158],"quality":[162],"output":[165],"rankings":[166],"after":[167],"having":[168],"applied":[169],"our":[170],"techniques.":[171]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}