{"id":"https://openalex.org/W2154347386","doi":"https://doi.org/10.1145/1841909.1841912","title":"Mining Historic Query Trails to Label Long and Rare Search Engine Queries","display_name":"Mining Historic Query Trails to Label Long and Rare Search Engine Queries","publication_year":2010,"publication_date":"2010-09-01","ids":{"openalex":"https://openalex.org/W2154347386","doi":"https://doi.org/10.1145/1841909.1841912","mag":"2154347386"},"language":"en","primary_location":{"id":"doi:10.1145/1841909.1841912","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1841909.1841912","pdf_url":null,"source":{"id":"https://openalex.org/S131231701","display_name":"ACM Transactions on the Web","issn_l":"1559-1131","issn":["1559-1131","1559-114X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on the Web","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/A5017503948","display_name":"Peter Bailey","orcid":null},"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":true,"raw_author_name":"Peter Bailey","raw_affiliation_strings":["Microsoft"],"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076259865","display_name":"Ryen W. White","orcid":"https://orcid.org/0000-0002-0265-4249"},"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":"Ryen W. White","raw_affiliation_strings":["Microsoft Research"],"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100349058","display_name":"Han Liu","orcid":"https://orcid.org/0000-0003-0647-6627"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Han Liu","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108530207","display_name":"Giridhar Kumaran","orcid":null},"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":"Giridhar Kumaran","raw_affiliation_strings":["Microsoft"],"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5017503948"],"corresponding_institution_ids":["https://openalex.org/I4210164937"],"apc_list":null,"apc_paid":null,"fwci":8.3244,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.974729,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"4","issue":"4","first_page":"1","last_page":"27"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9994999766349792,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9994999766349792,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9966999888420105,"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/T11106","display_name":"Data Management and Algorithms","score":0.9940000176429749,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.8242108821868896},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7566152811050415},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.7288864254951477},{"id":"https://openalex.org/keywords/web-query-classification","display_name":"Web query classification","score":0.6429917812347412},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.6403374075889587},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.5850374698638916},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5762925744056702},{"id":"https://openalex.org/keywords/directory","display_name":"Directory","score":0.5673627257347107},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.5211405754089355},{"id":"https://openalex.org/keywords/spatial-query","display_name":"Spatial query","score":0.5125934481620789},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5054945945739746},{"id":"https://openalex.org/keywords/sargable","display_name":"Sargable","score":0.5019519329071045},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.4993259906768799},{"id":"https://openalex.org/keywords/query-language","display_name":"Query language","score":0.46592211723327637},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.348616361618042},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.15554139018058777},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09499052166938782}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8242108821868896},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7566152811050415},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.7288864254951477},{"id":"https://openalex.org/C118689300","wikidata":"https://www.wikidata.org/wiki/Q7978614","display_name":"Web query classification","level":4,"score":0.6429917812347412},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.6403374075889587},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.5850374698638916},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5762925744056702},{"id":"https://openalex.org/C2777683733","wikidata":"https://www.wikidata.org/wiki/Q201456","display_name":"Directory","level":2,"score":0.5673627257347107},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.5211405754089355},{"id":"https://openalex.org/C172722865","wikidata":"https://www.wikidata.org/wiki/Q2302053","display_name":"Spatial query","level":5,"score":0.5125934481620789},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5054945945739746},{"id":"https://openalex.org/C192939062","wikidata":"https://www.wikidata.org/wiki/Q104840822","display_name":"Sargable","level":4,"score":0.5019519329071045},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.4993259906768799},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.46592211723327637},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.348616361618042},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15554139018058777},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09499052166938782},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1841909.1841912","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1841909.1841912","pdf_url":null,"source":{"id":"https://openalex.org/S131231701","display_name":"ACM Transactions on the Web","issn_l":"1559-1131","issn":["1559-1131","1559-114X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on the Web","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W86887328","https://openalex.org/W169253896","https://openalex.org/W1482214997","https://openalex.org/W1555108314","https://openalex.org/W1646006088","https://openalex.org/W1863141190","https://openalex.org/W1964384602","https://openalex.org/W1973103963","https://openalex.org/W1973430024","https://openalex.org/W1980515494","https://openalex.org/W1982835105","https://openalex.org/W1985182453","https://openalex.org/W1986475174","https://openalex.org/W1995262888","https://openalex.org/W1998548536","https://openalex.org/W2002388301","https://openalex.org/W2019045686","https://openalex.org/W2023408138","https://openalex.org/W2025356973","https://openalex.org/W2037124948","https://openalex.org/W2051834357","https://openalex.org/W2066343754","https://openalex.org/W2067472300","https://openalex.org/W2069870183","https://openalex.org/W2085030399","https://openalex.org/W2093390569","https://openalex.org/W2098876286","https://openalex.org/W2102914327","https://openalex.org/W2105106523","https://openalex.org/W2111216736","https://openalex.org/W2125771191","https://openalex.org/W2131345120","https://openalex.org/W2133156844","https://openalex.org/W2136542423","https://openalex.org/W2149393279","https://openalex.org/W2155540986","https://openalex.org/W2158450083","https://openalex.org/W2163375626","https://openalex.org/W2165476871","https://openalex.org/W2171806843","https://openalex.org/W4206765718","https://openalex.org/W4240913316"],"related_works":["https://openalex.org/W2096359267","https://openalex.org/W2572349046","https://openalex.org/W2026738364","https://openalex.org/W2146885082","https://openalex.org/W1981131819","https://openalex.org/W2392799717","https://openalex.org/W3125756434","https://openalex.org/W2124814993","https://openalex.org/W2017989738","https://openalex.org/W906795786"],"abstract_inverted_index":{"Web":[0],"search":[1,40,55,83,217,272,307,315],"engines":[2],"can":[3,34,73,266],"perform":[4],"poorly":[5],"for":[6,122,163,306,317],"long":[7,32,101,141,174,257,318],"queries":[8,33,62,102,128,147,224],"(i.e.,":[9],"those":[10],"containing":[11],"four":[12,160],"or":[13,58,86,116,296],"more":[14],"terms),":[15],"in":[16,50,111,150,203,245,279],"part":[17],"because":[18,114],"of":[19,23,29,37,93,126,139,159,167,205,301],"their":[20],"high":[21],"level":[22],"query":[24,68,88,97,144,185,252,288],"specificity.":[25],"The":[26,299],"automatic":[27,165],"assignment":[28,166],"labels":[30,64,72,172,265],"to":[31,109,132,173,236,269,275,310],"capture":[35],"aspects":[36],"a":[38,140,215,276],"user\u2019s":[39],"intent":[41],"that":[42,194,211,232,263,284],"may":[43,129],"not":[44,286],"be":[45,74,130,267],"apparent":[46],"from":[47,76,80,87,188],"the":[48,51,67,91,146,157,164,196,228,239,256],"terms":[49,204],"query.":[52,260],"This":[53],"affords":[54],"result":[56,84,218],"matching":[57,181],"reranking":[59],"based":[60,178],"on":[61,180,214],"and":[63,142,145,175,207,258],"rather":[65],"than":[66,243],"text":[69],"alone.":[70],"Query":[71],"derived":[75],"interaction":[77],"logs":[78],"generated":[79],"many":[81],"users\u2019":[82],"clicks":[85],"trails":[89,186],"comprising":[90],"chain":[92],"URLs":[94],"visited":[95],"following":[96],"submission.":[98],"However,":[99],"since":[100],"are":[103,107],"typically":[104],"rare,":[105],"they":[106],"difficult":[108],"label":[110,241],"this":[112,153],"way":[113],"little":[115],"no":[117,250],"historic":[118],"log":[119,189],"data":[120],"exists":[121],"them.":[123],"A":[124],"subset":[125],"these":[127,264],"amenable":[131],"labeling":[133],"by":[134],"detecting":[135],"similarities":[136],"between":[137],"parts":[138],"rare":[143,176,259],"which":[148],"appear":[149],"logs.":[151,298],"In":[152],"article,":[154],"we":[155,199],"present":[156],"comparison":[158],"similarity":[161,213],"algorithms":[162,198],"Open":[168],"Directory":[169],"Project":[170],"category":[171],"queries,":[177],"solely":[179],"against":[182],"similar":[183],"satisfied":[184],"extracted":[187],"data.":[190],"Our":[191],"findings":[192],"show":[193,262],"although":[195],"similarity-matching":[197],"investigated":[200],"have":[201,304],"tradeoffs":[202],"coverage":[206],"accuracy,":[208],"one":[209,244],"algorithm":[210],"bases":[212],"popular":[216],"ranking":[219],"function":[220],"(effectively":[221],"regarding":[222],"potentially-similar":[223],"as":[225],"\u201cdocuments\u201d)":[226],"outperforms":[227],"others.":[229],"We":[230,261],"find":[231],"it":[233],"is":[234],"possible":[235],"correctly":[237],"predict":[238],"top":[240],"better":[242],"five":[246],"times,":[247],"even":[248],"when":[249],"past":[251],"trail":[253],"exactly":[254],"matches":[255],"used":[268],"reorder":[270],"top-ranked":[271],"results":[273,293,316],"leading":[274],"significant":[277],"improvement":[278],"retrieval":[280],"performance":[281],"over":[282],"baselines":[283],"do":[285],"utilize":[287],"labeling,":[289],"but":[290],"instead":[291],"rank":[292],"using":[294],"content-matching":[295],"click-through":[297],"outcomes":[300],"our":[302],"research":[303],"implications":[305],"providers":[308],"attempting":[309],"provide":[311],"users":[312],"with":[313],"highly-relevant":[314],"queries.":[319]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":6},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}