{"id":"https://openalex.org/W1995262888","doi":"https://doi.org/10.1145/1229179.1229183","title":"Automatic classification of Web queries using very large unlabeled query logs","display_name":"Automatic classification of Web queries using very large unlabeled query logs","publication_year":2007,"publication_date":"2007-04-01","ids":{"openalex":"https://openalex.org/W1995262888","doi":"https://doi.org/10.1145/1229179.1229183","mag":"1995262888"},"language":"en","primary_location":{"id":"doi:10.1145/1229179.1229183","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1229179.1229183","pdf_url":null,"source":{"id":"https://openalex.org/S4394735545","display_name":"ACM Transactions on Information Systems","issn_l":"1046-8188","issn":["1046-8188","1558-2868"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Information Systems","raw_type":"journal-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/A5090267689","display_name":"Steven M. Beitzel","orcid":null},"institutions":[{"id":"https://openalex.org/I180949307","display_name":"Illinois Institute of Technology","ror":"https://ror.org/037t3ry66","country_code":"US","type":"education","lineage":["https://openalex.org/I180949307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Steven M. Beitzel","raw_affiliation_strings":["Illinois Institute of Technology, Chicago, IL",", Illinois Institute of Technology, Chicago, IL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Illinois Institute of Technology, Chicago, IL","institution_ids":["https://openalex.org/I180949307"]},{"raw_affiliation_string":", Illinois Institute of Technology, Chicago, IL","institution_ids":["https://openalex.org/I180949307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064265420","display_name":"Eric C. Jensen","orcid":null},"institutions":[{"id":"https://openalex.org/I180949307","display_name":"Illinois Institute of Technology","ror":"https://ror.org/037t3ry66","country_code":"US","type":"education","lineage":["https://openalex.org/I180949307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric C. Jensen","raw_affiliation_strings":["Illinois Institute of Technology, Chicago, IL",", Illinois Institute of Technology, Chicago, IL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Illinois Institute of Technology, Chicago, IL","institution_ids":["https://openalex.org/I180949307"]},{"raw_affiliation_string":", Illinois Institute of Technology, Chicago, IL","institution_ids":["https://openalex.org/I180949307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104594596","display_name":"David D. Lewis","orcid":null},"institutions":[{"id":"https://openalex.org/I4210148173","display_name":"Morgan, Lewis & Bockius (United States)","ror":"https://ror.org/04c0z3e83","country_code":"US","type":"company","lineage":["https://openalex.org/I4210148173"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David D. Lewis","raw_affiliation_strings":["David D. Lewis Consulting, Chicago, IL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"David D. Lewis Consulting, Chicago, IL","institution_ids":["https://openalex.org/I4210148173"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103951527","display_name":"Abdur Chowdhury","orcid":null},"institutions":[{"id":"https://openalex.org/I180949307","display_name":"Illinois Institute of Technology","ror":"https://ror.org/037t3ry66","country_code":"US","type":"education","lineage":["https://openalex.org/I180949307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abdur Chowdhury","raw_affiliation_strings":["Illinois Institute of Technology, Chicago, IL",", Illinois Institute of Technology, Chicago, IL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Illinois Institute of Technology, Chicago, IL","institution_ids":["https://openalex.org/I180949307"]},{"raw_affiliation_string":", Illinois Institute of Technology, Chicago, IL","institution_ids":["https://openalex.org/I180949307"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110275365","display_name":"Ophir Frieder","orcid":null},"institutions":[{"id":"https://openalex.org/I180949307","display_name":"Illinois Institute of Technology","ror":"https://ror.org/037t3ry66","country_code":"US","type":"education","lineage":["https://openalex.org/I180949307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ophir Frieder","raw_affiliation_strings":["Illinois Institute of Technology, Chicago, IL",", Illinois Institute of Technology, Chicago, IL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Illinois Institute of Technology, Chicago, IL","institution_ids":["https://openalex.org/I180949307"]},{"raw_affiliation_string":", Illinois Institute of Technology, Chicago, IL","institution_ids":["https://openalex.org/I180949307"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":29.6424,"has_fulltext":false,"cited_by_count":106,"citation_normalized_percentile":{"value":0.99538723,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"25","issue":"2","first_page":"9","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9965999722480774,"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":0.9965999722480774,"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":0.9957000017166138,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.992900013923645,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8981980085372925},{"id":"https://openalex.org/keywords/web-query-classification","display_name":"Web query classification","score":0.688125491142273},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.62144935131073},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.5520511269569397},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.4574337601661682},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.44731175899505615},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.43963387608528137},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.43847617506980896},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4382930397987366},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.419039785861969},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1774013340473175}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8981980085372925},{"id":"https://openalex.org/C118689300","wikidata":"https://www.wikidata.org/wiki/Q7978614","display_name":"Web query classification","level":4,"score":0.688125491142273},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.62144935131073},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.5520511269569397},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.4574337601661682},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.44731175899505615},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.43963387608528137},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.43847617506980896},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4382930397987366},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.419039785861969},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1774013340473175},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1229179.1229183","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1229179.1229183","pdf_url":null,"source":{"id":"https://openalex.org/S4394735545","display_name":"ACM Transactions on Information Systems","issn_l":"1046-8188","issn":["1046-8188","1558-2868"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Information Systems","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.97.4431","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.97.4431","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cchen1.csie.ntust.edu.tw/students/2009/Automatic classification of Web queries using very large unlabeled query logs.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":62,"referenced_works":["https://openalex.org/W21704922","https://openalex.org/W29496115","https://openalex.org/W95791645","https://openalex.org/W126924136","https://openalex.org/W179016587","https://openalex.org/W1481308070","https://openalex.org/W1493246353","https://openalex.org/W1516391399","https://openalex.org/W1525460779","https://openalex.org/W1533748861","https://openalex.org/W1534714852","https://openalex.org/W1574525710","https://openalex.org/W1574901103","https://openalex.org/W1576520375","https://openalex.org/W1586405805","https://openalex.org/W1588320668","https://openalex.org/W1604938182","https://openalex.org/W1911857613","https://openalex.org/W1963485567","https://openalex.org/W1963726077","https://openalex.org/W1972645849","https://openalex.org/W1973867972","https://openalex.org/W1983671927","https://openalex.org/W1985182453","https://openalex.org/W1986475174","https://openalex.org/W1997948332","https://openalex.org/W1998548536","https://openalex.org/W2000826169","https://openalex.org/W2007807439","https://openalex.org/W2010463775","https://openalex.org/W2022122406","https://openalex.org/W2029341294","https://openalex.org/W2041179002","https://openalex.org/W2044206629","https://openalex.org/W2054882585","https://openalex.org/W2057970600","https://openalex.org/W2064522604","https://openalex.org/W2066341057","https://openalex.org/W2066343754","https://openalex.org/W2096623622","https://openalex.org/W2099111195","https://openalex.org/W2118020653","https://openalex.org/W2124449410","https://openalex.org/W2143257555","https://openalex.org/W2147164982","https://openalex.org/W2149600263","https://openalex.org/W2153962014","https://openalex.org/W2154724067","https://openalex.org/W2155540986","https://openalex.org/W2156037541","https://openalex.org/W2156961248","https://openalex.org/W2157748587","https://openalex.org/W2165612380","https://openalex.org/W2168621303","https://openalex.org/W2170471032","https://openalex.org/W2170714116","https://openalex.org/W4252417799","https://openalex.org/W4255380597","https://openalex.org/W6605815150","https://openalex.org/W6634442568","https://openalex.org/W6655659674","https://openalex.org/W6738852829"],"related_works":["https://openalex.org/W2096359267","https://openalex.org/W2026738364","https://openalex.org/W2901901036","https://openalex.org/W3008917487","https://openalex.org/W2124814993","https://openalex.org/W1521725692","https://openalex.org/W2093300859","https://openalex.org/W2013069866","https://openalex.org/W2113390685","https://openalex.org/W3197639690"],"abstract_inverted_index":{"Accurate":[0],"topical":[1],"classification":[2,18,38],"of":[3,30,63,85,119,129,155,216,224],"user":[4],"queries":[5,26,45,114,156],"allows":[6],"for":[7,135,227],"increased":[8],"effectiveness":[9],"and":[10,32,61,80,96,163,195],"efficiency":[11],"in":[12,83,137,229],"general-purpose":[13],"Web":[14,44,124,144,160],"search":[15,145,161],"systems.":[16],"Such":[17],"becomes":[19],"critical":[20],"if":[21],"the":[22,57,127,175,191,217],"system":[23],"must":[24],"route":[25],"to":[27,188,210],"a":[28,40,97,106,152,213],"subset":[29],"topic-specific":[31],"resource-constrained":[33],"back-end":[34],"databases.":[35],"Successful":[36],"query":[37,109,218],"poses":[39],"challenging":[41],"problem,":[42],"as":[43,122,142],"are":[46],"short,":[47],"thus":[48],"providing":[49],"few":[50],"features.":[51],"This":[52,205],"feature":[53],"sparseness,":[54],"coupled":[55],"with":[56],"constantly":[58],"changing":[59],"distribution":[60],"vocabulary":[62],"queries,":[64,89],"hinders":[65],"traditional":[66],"text":[67],"classification.":[68],"We":[69,147],"attack":[70],"this":[71],"problem":[72],"by":[73,93,171],"combining":[74],"multiple":[75],"classifiers,":[76],"including":[77],"exact":[78],"lookup":[79],"partial":[81],"matching":[82],"databases":[84],"manually":[86],"classified":[87],"frequent":[88],"linear":[90],"models":[91],"trained":[92],"supervised":[94],"learning,":[95],"novel":[98],"approach":[99,112,150],"based":[100],"on":[101],"mining":[102],"selectional":[103],"preferences":[104],"from":[105,157,190],"large":[107,153],"unlabeled":[108],"log.":[110],"Our":[111],"classifies":[113],"without":[115,220],"using":[116,151],"external":[117,222],"sources":[118,223],"information,":[120,225],"such":[121,141],"online":[123],"directories":[125],"or":[126],"contents":[128],"retrieved":[130],"pages,":[131],"making":[132],"it":[133,207],"viable":[134],"use":[136],"demanding":[138],"operational":[139,159,203],"environments,":[140],"large-scale":[143],"services.":[146],"evaluate":[148],"our":[149,166,186,202],"sample":[154],"an":[158],"engine":[162],"show":[164],"that":[165,197],"combined":[167],"method":[168,178],"increases":[169],"recall":[170],"nearly":[172],"40%":[173],"over":[174],"best":[176],"single":[177],"while":[179],"maintaining":[180],"adequate":[181],"precision.":[182],"Additionally,":[183],"we":[184,198],"compare":[185],"results":[187],"those":[189],"2005":[192],"KDD":[193],"Cup":[194],"find":[196],"perform":[199],"competitively":[200],"despite":[201],"restrictions.":[204],"suggests":[206],"is":[208],"possible":[209],"topically":[211],"classify":[212],"significant":[214],"portion":[215],"stream":[219],"requiring":[221],"allowing":[226],"deployment":[228],"operationally":[230],"restricted":[231],"environments.":[232]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":9}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
