{"id":"https://openalex.org/W2139527693","doi":"https://doi.org/10.1145/1935826.1935859","title":"Detecting duplicate web documents using clickthrough data","display_name":"Detecting duplicate web documents using clickthrough data","publication_year":2011,"publication_date":"2011-02-01","ids":{"openalex":"https://openalex.org/W2139527693","doi":"https://doi.org/10.1145/1935826.1935859","mag":"2139527693"},"language":"en","primary_location":{"id":"doi:10.1145/1935826.1935859","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1935826.1935859","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the fourth ACM international conference on Web search and data mining","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/A5081692910","display_name":"Filip Radlinski","orcid":"https://orcid.org/0000-0002-1386-9288"},"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"]},{"id":"https://openalex.org/I4210153468","display_name":"Microsoft (Canada)","ror":"https://ror.org/04xhxg104","country_code":"CA","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210153468"]}],"countries":["CA","US"],"is_corresponding":false,"raw_author_name":"Filip Radlinski","raw_affiliation_strings":["Microsoft, Vancouver, BC, Canada","[Microsoft, Vancouver, BC, Canada]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, Vancouver, BC, Canada","institution_ids":["https://openalex.org/I4210153468"]},{"raw_affiliation_string":"[Microsoft, Vancouver, BC, Canada]","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102869952","display_name":"Paul N. Bennett","orcid":"https://orcid.org/0000-0002-8846-5480"},"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":"Paul N. Bennett","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076265623","display_name":"Emine Y\u0131lmaz","orcid":"https://orcid.org/0000-0002-3434-8932"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Emine Yilmaz","raw_affiliation_strings":["Microsoft, Cambridge, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"147","last_page":"156"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9987000226974487,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.998199999332428,"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":0.8268651962280273},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7879881858825684},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.6681115627288818},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.5073534846305847},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.45070597529411316},{"id":"https://openalex.org/keywords/web-query-classification","display_name":"Web query classification","score":0.44117921590805054},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.3759532570838928},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3279900550842285},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13713431358337402}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8268651962280273},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7879881858825684},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.6681115627288818},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.5073534846305847},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.45070597529411316},{"id":"https://openalex.org/C118689300","wikidata":"https://www.wikidata.org/wiki/Q7978614","display_name":"Web query classification","level":4,"score":0.44117921590805054},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.3759532570838928},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3279900550842285},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13713431358337402},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1935826.1935859","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1935826.1935859","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the fourth ACM international conference on Web search and data mining","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.296.2995","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.296.2995","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/en-us/um/people/pauben/papers/WSDM2011-Radlinski-Bennett-Yilmaz.pdf","raw_type":"text"},{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:1421701","is_oa":false,"landing_page_url":"http://discovery.ucl.ac.uk/1421701/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"In: King, I and Nejdl, W and Li, H, (eds.) (pp. pp. 147-156). ACM (2011)","raw_type":"Proceedings paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1498594556","https://openalex.org/W1532325895","https://openalex.org/W1546477643","https://openalex.org/W1594031697","https://openalex.org/W1787140601","https://openalex.org/W1974360117","https://openalex.org/W1978658266","https://openalex.org/W1980730196","https://openalex.org/W1987500252","https://openalex.org/W1992549066","https://openalex.org/W1993320088","https://openalex.org/W2012833704","https://openalex.org/W2037098674","https://openalex.org/W2047221353","https://openalex.org/W2058732827","https://openalex.org/W2067432306","https://openalex.org/W2083305840","https://openalex.org/W2104895009","https://openalex.org/W2109803107","https://openalex.org/W2110166424","https://openalex.org/W2113640060","https://openalex.org/W2123937625","https://openalex.org/W2133990480","https://openalex.org/W2142927605","https://openalex.org/W2148885851","https://openalex.org/W2151592910","https://openalex.org/W2152228468","https://openalex.org/W2152565070","https://openalex.org/W2156037541","https://openalex.org/W2156160882","https://openalex.org/W2157128462","https://openalex.org/W2159048649","https://openalex.org/W2170121748","https://openalex.org/W2197919320","https://openalex.org/W3138773240","https://openalex.org/W4230624213","https://openalex.org/W6843735874"],"related_works":["https://openalex.org/W2026738364","https://openalex.org/W2096359267","https://openalex.org/W2901901036","https://openalex.org/W2124814993","https://openalex.org/W2163573236","https://openalex.org/W2113390685","https://openalex.org/W3114052401","https://openalex.org/W2330073594","https://openalex.org/W2533706070","https://openalex.org/W2105258824"],"abstract_inverted_index":{"The":[0],"web":[1],"contains":[2],"many":[3],"duplicate":[4,31,54],"and":[5],"near-duplicate":[6],"documents.":[7],"Given":[8],"that":[9,49,60],"user":[10,69],"satisfaction":[11],"is":[12,56],"negatively":[13],"affected":[14],"by":[15],"redundant":[16,62],"information":[17,63],"in":[18],"search":[19],"results,":[20],"a":[21,50,67,78,90],"significant":[22],"amount":[23],"of":[24,53,89],"research":[25],"has":[26],"been":[27],"devoted":[28],"to":[29,43,57,66,83],"developing":[30],"detection":[32,55],"algorithms.":[33],"However,":[34],"most":[35],"such":[36],"algorithms":[37,76],"rely":[38],"solely":[39],"on":[40,86],"document":[41],"content":[42,92],"detect":[44],"duplication,":[45],"ignoring":[46],"the":[47,87],"fact":[48],"primary":[51],"goal":[52],"identify":[58],"documents":[59],"contain":[61],"with":[64],"respect":[65],"particular":[68],"query.":[70],"Similarly,":[71],"although":[72],"query-dependent":[73,79],"result":[74],"diversification":[75],"compute":[77],"ranking,":[80],"they":[81],"tend":[82],"do":[84],"so":[85],"basis":[88],"query-independent":[91],"similarity":[93],"score.":[94]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}
