{"id":"https://openalex.org/W2344430697","doi":"https://doi.org/10.3233/web-160335","title":"Accurate and efficient query clustering via top ranked search results","display_name":"Accurate and efficient query clustering via top ranked search results","publication_year":2016,"publication_date":"2016-04-25","ids":{"openalex":"https://openalex.org/W2344430697","doi":"https://doi.org/10.3233/web-160335","mag":"2344430697"},"language":"en","primary_location":{"id":"doi:10.3233/web-160335","is_oa":false,"landing_page_url":"https://doi.org/10.3233/web-160335","pdf_url":null,"source":{"id":"https://openalex.org/S4210183871","display_name":"Web Intelligence","issn_l":"2405-6456","issn":["2405-6456","2405-6464"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Web Intelligence","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/A5100725148","display_name":"Yuan Hong","orcid":"https://orcid.org/0000-0003-4095-4506"},"institutions":[{"id":"https://openalex.org/I392282","display_name":"University at Albany, State University of New York","ror":"https://ror.org/012zs8222","country_code":"US","type":"education","lineage":["https://openalex.org/I392282"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yuan Hong","raw_affiliation_strings":["Department of Information Technology Management, University at Albany, SUNY, USA. E-mail:\u00a0","Department of Information Technology Management, University at Albany, SUNY, USA. E-mail:\u00a0hong@albany.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Technology Management, University at Albany, SUNY, USA. E-mail:\u00a0","institution_ids":["https://openalex.org/I392282"]},{"raw_affiliation_string":"Department of Information Technology Management, University at Albany, SUNY, USA. E-mail:\u00a0hong@albany.edu","institution_ids":["https://openalex.org/I392282"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034878799","display_name":"Jaideep Vaidya","orcid":"https://orcid.org/0000-0002-7420-6947"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]},{"id":"https://openalex.org/I4210096112","display_name":"Rutgers Sexual and Reproductive Health and Rights","ror":"https://ror.org/00rcvgx40","country_code":"NL","type":"other","lineage":["https://openalex.org/I4210096112"]}],"countries":["NL","US"],"is_corresponding":false,"raw_author_name":"Jaideep Vaidya","raw_affiliation_strings":["Department of Management Science and Information Systems, Rutgers University, USA. E-mail:\u00a0","Department of Management Science and Information Systems, Rutgers University, USA. E-mail:\u00a0jsvaidya@business.rutgers.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Management Science and Information Systems, Rutgers University, USA. E-mail:\u00a0","institution_ids":["https://openalex.org/I4210096112"]},{"raw_affiliation_string":"Department of Management Science and Information Systems, Rutgers University, USA. E-mail:\u00a0jsvaidya@business.rutgers.edu","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060287641","display_name":"Haibing Lu","orcid":"https://orcid.org/0000-0003-0266-6191"},"institutions":[{"id":"https://openalex.org/I16269868","display_name":"Santa Clara University","ror":"https://ror.org/03ypqe447","country_code":"US","type":"education","lineage":["https://openalex.org/I16269868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haibing Lu","raw_affiliation_strings":["Department of Operations and Management Information Systems, Santa Clara University, USA. E-mail:\u00a0","Department of Operations and Management Information Systems, Santa Clara University, USA. E-mail:\u00a0hlu@scu.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Operations and Management Information Systems, Santa Clara University, USA. E-mail:\u00a0","institution_ids":["https://openalex.org/I16269868"]},{"raw_affiliation_string":"Department of Operations and Management Information Systems, Santa Clara University, USA. E-mail:\u00a0hlu@scu.edu","institution_ids":["https://openalex.org/I16269868"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071378916","display_name":"Wen Ming Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210148195","display_name":"Concordia University","ror":"https://ror.org/04dwckp88","country_code":"US","type":"education","lineage":["https://openalex.org/I4210148195"]},{"id":"https://openalex.org/I60158472","display_name":"Concordia University","ror":"https://ror.org/0420zvk78","country_code":"CA","type":"education","lineage":["https://openalex.org/I60158472"]}],"countries":["CA","US"],"is_corresponding":false,"raw_author_name":"Wen Ming Liu","raw_affiliation_strings":["Concordia Institute for Information Systems Engineering, Concordia University, Montreal, Canada. E-mail:\u00a0","Concordia Institute for Information Systems Engineering, Concordia University, Montreal, Canada. E-mail:\u00a0l_wenmin@ciise.concordia.ca"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Concordia Institute for Information Systems Engineering, Concordia University, Montreal, Canada. E-mail:\u00a0","institution_ids":["https://openalex.org/I4210148195","https://openalex.org/I60158472"]},{"raw_affiliation_string":"Concordia Institute for Information Systems Engineering, Concordia University, Montreal, Canada. E-mail:\u00a0l_wenmin@ciise.concordia.ca","institution_ids":["https://openalex.org/I60158472"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100725148"],"corresponding_institution_ids":["https://openalex.org/I392282"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.03102725,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"14","issue":"2","first_page":"119","last_page":"138"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9990000128746033,"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"}},"topics":[{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9990000128746033,"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"}},{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9975000023841858,"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/T11478","display_name":"Caching and Content Delivery","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.7841644287109375},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7361692786216736},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6488531827926636},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5523362159729004},{"id":"https://openalex.org/keywords/dbscan","display_name":"DBSCAN","score":0.5010809898376465},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.4896726906299591},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.47394445538520813},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.46540695428848267},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.43621179461479187},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.4340243339538574},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4280996024608612},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.41808170080184937},{"id":"https://openalex.org/keywords/fuzzy-clustering","display_name":"Fuzzy clustering","score":0.386112242937088},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.2791624963283539},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.21752041578292847},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.18258130550384521}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7841644287109375},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7361692786216736},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6488531827926636},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5523362159729004},{"id":"https://openalex.org/C46576248","wikidata":"https://www.wikidata.org/wiki/Q1114630","display_name":"DBSCAN","level":5,"score":0.5010809898376465},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.4896726906299591},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.47394445538520813},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.46540695428848267},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.43621179461479187},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.4340243339538574},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4280996024608612},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.41808170080184937},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.386112242937088},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.2791624963283539},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.21752041578292847},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18258130550384521},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/web-160335","is_oa":false,"landing_page_url":"https://doi.org/10.3233/web-160335","pdf_url":null,"source":{"id":"https://openalex.org/S4210183871","display_name":"Web Intelligence","issn_l":"2405-6456","issn":["2405-6456","2405-6464"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Web Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W20984399","https://openalex.org/W296815351","https://openalex.org/W1495202631","https://openalex.org/W1498745611","https://openalex.org/W1520082916","https://openalex.org/W1564094940","https://openalex.org/W1565377632","https://openalex.org/W1592827165","https://openalex.org/W1673310716","https://openalex.org/W1740509135","https://openalex.org/W1966835268","https://openalex.org/W1972645849","https://openalex.org/W1973063178","https://openalex.org/W1973867972","https://openalex.org/W2027752285","https://openalex.org/W2028213751","https://openalex.org/W2029559422","https://openalex.org/W2041179002","https://openalex.org/W2047221353","https://openalex.org/W2048476252","https://openalex.org/W2051224630","https://openalex.org/W2084246508","https://openalex.org/W2086378526","https://openalex.org/W2099391294","https://openalex.org/W2099548400","https://openalex.org/W2101552389","https://openalex.org/W2108368547","https://openalex.org/W2123656745","https://openalex.org/W2125771191","https://openalex.org/W2134131174","https://openalex.org/W2134834365","https://openalex.org/W2146717104","https://openalex.org/W2149469409","https://openalex.org/W2150930471","https://openalex.org/W2152485467","https://openalex.org/W2160555926","https://openalex.org/W2163676312","https://openalex.org/W2167554129","https://openalex.org/W2171683557","https://openalex.org/W2171743956","https://openalex.org/W2172127413","https://openalex.org/W4241676240","https://openalex.org/W4245150116","https://openalex.org/W4248182554","https://openalex.org/W4256046779","https://openalex.org/W6600561556","https://openalex.org/W6631872075"],"related_works":["https://openalex.org/W1521725692","https://openalex.org/W2096359267","https://openalex.org/W3008917487","https://openalex.org/W3197639690","https://openalex.org/W2026738364","https://openalex.org/W2572349046","https://openalex.org/W2901901036","https://openalex.org/W2185998359","https://openalex.org/W2381709896","https://openalex.org/W3194422352"],"abstract_inverted_index":{"To":[0],"make":[1],"the":[2,153,159,167,175,190],"search":[3,8,96,107],"engine":[4],"more":[5,195],"user-friendly,":[6],"commercial":[7],"engines":[9],"commonly":[10],"develop":[11,136],"applications":[12],"to":[13,31,113,135,151],"provide":[14],"suggestion":[15],"or":[16,59],"recommendation":[17],"for":[18,94,127],"every":[19],"posed":[20],"query.":[21],"Clustering":[22],"semantically":[23],"similar":[24],"queries":[25,39,97],"acts":[26],"as":[27,57],"an":[28],"essential":[29],"prerequisite":[30],"function":[32],"well":[33],"in":[34,65,144],"those":[35,129],"applications.":[36],"However,":[37],"clustering":[38,54,79,95],"effectively":[40],"is":[41,84],"quite":[42,86],"challenging,":[43],"since":[44],"they":[45],"are":[46],"usually":[47],"short,":[48],"incomplete":[49],"and":[50,140,172,189],"ambiguous.":[51],"Existing":[52],"prevalent":[53],"methods,":[55],"such":[56,66,119],"K-Means":[58],"DBSCAN":[60],"cannot":[61],"guarantee":[62],"good":[63,81],"performance":[64],"a":[67,91,100,123,199],"highly":[68],"dimensional":[69],"environment.":[70],"Through":[71],"analyzing":[72],"users\u2019":[73],"click-through":[74],"query":[75,115,145],"logs,":[76],"hierarchical":[77],"agglomerative":[78],"gives":[80],"results":[82,108,176,183,197],"but":[83],"computationally":[85],"expensive.":[87],"This":[88,132],"paper":[89],"identifies":[90],"novel":[92],"feature":[93],"based":[98],"on":[99],"key":[101],"insight":[102],"\u2013":[103],"queries\u2019":[104],"top":[105],"ranked":[106],"can":[109,193],"themselves":[110],"be":[111],"used":[112],"quantify":[114],"similarity.":[116],"After":[117],"investigating":[118],"feature,":[120],"we":[121],"propose":[122],"new":[124],"similarity":[125,191],"metric":[126,192],"comparing":[128],"diverse":[130],"queries.":[131],"facilitates":[133],"us":[134],"two":[137,163,187],"very":[138],"efficient":[139],"accurate":[141,196],"algorithms":[142,188],"integrated":[143],"clustering.":[146],"We":[147],"conduct":[148],"comprehensive":[149],"experiments":[150],"compare":[152],"accuracy":[154],"of":[155,169],"our":[156,186],"approach":[157],"against":[158],"known":[160],"baselines":[161],"along":[162],"dimensions:":[164],"1)":[165],"quantifying":[166],"cohesion/separation":[168],"clustered":[170],"queries,":[171],"2)":[173],"justifying":[174],"by":[177],"real-world":[178],"Internet":[179],"users.":[180],"The":[181],"experimental":[182],"demonstrate":[184],"that":[185],"generate":[194],"within":[198],"significantly":[200],"shorter":[201],"time.":[202]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}