{"id":"https://openalex.org/W1980995378","doi":"https://doi.org/10.1145/1568292.1568295","title":"Web Search Clustering and Labeling with Hidden Topics","display_name":"Web Search Clustering and Labeling with Hidden Topics","publication_year":2009,"publication_date":"2009-08-01","ids":{"openalex":"https://openalex.org/W1980995378","doi":"https://doi.org/10.1145/1568292.1568295","mag":"1980995378"},"language":"en","primary_location":{"id":"doi:10.1145/1568292.1568295","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1568292.1568295","pdf_url":null,"source":{"id":"https://openalex.org/S56575750","display_name":"ACM Transactions on Asian Language Information Processing","issn_l":"1530-0226","issn":["1530-0226","1558-3430"],"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 Asian Language Information Processing","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/A5065000009","display_name":"Cam-Tu Nguyen","orcid":"https://orcid.org/0009-0006-9484-6876"},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Cam-Tu Nguyen","raw_affiliation_strings":["Tohoku University","Tohoku Univ.#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tohoku University","institution_ids":["https://openalex.org/I201537933"]},{"raw_affiliation_string":"Tohoku Univ.#TAB#","institution_ids":["https://openalex.org/I201537933"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012773199","display_name":"Xuan-Hieu Phan","orcid":"https://orcid.org/0000-0002-7640-9190"},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xuan-Hieu Phan","raw_affiliation_strings":["Tohoku University","Tohoku Univ.#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tohoku University","institution_ids":["https://openalex.org/I201537933"]},{"raw_affiliation_string":"Tohoku Univ.#TAB#","institution_ids":["https://openalex.org/I201537933"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112034357","display_name":"Susumu Horiguchi","orcid":null},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Susumu Horiguchi","raw_affiliation_strings":["Tohoku University","Tohoku Univ.#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tohoku University","institution_ids":["https://openalex.org/I201537933"]},{"raw_affiliation_string":"Tohoku Univ.#TAB#","institution_ids":["https://openalex.org/I201537933"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011481562","display_name":"Thu-Trang Nguyen","orcid":"https://orcid.org/0000-0002-3596-2352"},"institutions":[{"id":"https://openalex.org/I123565023","display_name":"Vietnam National University Ho Chi Minh City","ror":"https://ror.org/00waaqh38","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Thu-Trang Nguyen","raw_affiliation_strings":["Vietnam National University","Vietnam national university"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vietnam National University","institution_ids":["https://openalex.org/I123565023"]},{"raw_affiliation_string":"Vietnam national university","institution_ids":["https://openalex.org/I123565023"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071516373","display_name":"Quang-Thuy Ha","orcid":"https://orcid.org/0000-0002-3901-3357"},"institutions":[{"id":"https://openalex.org/I123565023","display_name":"Vietnam National University Ho Chi Minh City","ror":"https://ror.org/00waaqh38","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Quang-Thuy Ha","raw_affiliation_strings":["Vietnam National University","Vietnam national university"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vietnam National University","institution_ids":["https://openalex.org/I123565023"]},{"raw_affiliation_string":"Vietnam national university","institution_ids":["https://openalex.org/I123565023"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.9827,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.95001121,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"8","issue":"3","first_page":"1","last_page":"40"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9940000176429749,"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"}},"topics":[{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9940000176429749,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9937000274658203,"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/T11106","display_name":"Data Management and Algorithms","score":0.9796000123023987,"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":0.8606681227684021},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.8209317922592163},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.67423415184021},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.6272923350334167},{"id":"https://openalex.org/keywords/upload","display_name":"Upload","score":0.5220254063606262},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.4888164699077606},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.47296279668807983},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.41496390104293823},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.41352736949920654},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.40001213550567627},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.35657116770744324},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22427520155906677}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8606681227684021},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8209317922592163},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.67423415184021},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.6272923350334167},{"id":"https://openalex.org/C71901391","wikidata":"https://www.wikidata.org/wiki/Q7126699","display_name":"Upload","level":2,"score":0.5220254063606262},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.4888164699077606},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.47296279668807983},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.41496390104293823},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.41352736949920654},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40001213550567627},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.35657116770744324},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22427520155906677},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1568292.1568295","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1568292.1568295","pdf_url":null,"source":{"id":"https://openalex.org/S56575750","display_name":"ACM Transactions on Asian Language Information Processing","issn_l":"1530-0226","issn":["1530-0226","1558-3430"],"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 Asian Language Information Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W27634986","https://openalex.org/W164956183","https://openalex.org/W1529075208","https://openalex.org/W1552319112","https://openalex.org/W1573190978","https://openalex.org/W1880262756","https://openalex.org/W1965893683","https://openalex.org/W1996764654","https://openalex.org/W1996852448","https://openalex.org/W2001082470","https://openalex.org/W2040221623","https://openalex.org/W2043747172","https://openalex.org/W2072644219","https://openalex.org/W2073853190","https://openalex.org/W2088314245","https://openalex.org/W2110441437","https://openalex.org/W2110591510","https://openalex.org/W2113227740","https://openalex.org/W2113855231","https://openalex.org/W2120779048","https://openalex.org/W2121996546","https://openalex.org/W2128925311","https://openalex.org/W2132341030","https://openalex.org/W2135194391","https://openalex.org/W2141734078","https://openalex.org/W2147152072","https://openalex.org/W2147159144","https://openalex.org/W2149393279","https://openalex.org/W2152311353","https://openalex.org/W2157361576","https://openalex.org/W2161443453","https://openalex.org/W2169606435","https://openalex.org/W2171836785","https://openalex.org/W2615497679","https://openalex.org/W3099640513","https://openalex.org/W4241122026","https://openalex.org/W6676781583"],"related_works":["https://openalex.org/W2769501189","https://openalex.org/W4315588616","https://openalex.org/W4312773271","https://openalex.org/W2888805565","https://openalex.org/W2962686197","https://openalex.org/W2207653751","https://openalex.org/W2611137333","https://openalex.org/W3005513013","https://openalex.org/W4309228610","https://openalex.org/W4294597112"],"abstract_inverted_index":{"Web":[0,60,70,118],"search":[1,8,71],"clustering":[2,28,32,50,55,69,162,211],"is":[3,84,102,122,145],"a":[4,14,65,112,149,161,170,187],"solution":[5],"to":[6,104,192],"reorganize":[7],"results":[9,72],"(also":[10],"called":[11,155],"\u201csnippets\u201d)":[12],"in":[13,73,111],"more":[15],"convenient":[16],"way":[17],"for":[18,25,68],"browsing.":[19],"There":[20],"are":[21],"three":[22,78],"key":[23],"requirements":[24],"such":[26,108,130],"post-retrieval":[27],"systems:":[29],"(1)":[30],"the":[31,49,58,77,99,143,166,178],"algorithm":[33],"should":[34,41,52],"group":[35],"similar":[36],"documents":[37,97],"together;":[38],"(2)":[39],"clusters":[40],"be":[42,184,193],"labeled":[43],"with":[44,90],"descriptive":[45],"phrases;":[46],"and":[47,106,158,169,203],"(3)":[48],"system":[51,163],"provide":[53],"high-quality":[54],"without":[56,115],"downloading":[57],"whole":[59,117],"page.":[61],"This":[62,182],"article":[63],"introduces":[64],"novel":[66],"framework":[67,144],"Vietnamese":[74],"which":[75],"targets":[76],"above":[79],"issues.":[80],"The":[81,139],"main":[82],"motivation":[83],"that":[85,146,205],"by":[86],"enriching":[87],"short":[88],"snippets":[89,109,168,191],"hidden":[91,174],"topics":[92,175],"from":[93,177],"huge":[94],"resources":[95],"of":[96,142,173,190,200],"on":[98,124,164],"Internet,":[100],"it":[101],"able":[103],"cluster":[105],"label":[107],"effectively":[110],"topic-oriented":[113],"manner":[114],"concerning":[116],"pages.":[119],"Our":[120],"approach":[121],"based":[123],"recent":[125],"successful":[126],"topic":[127],"analysis":[128],"models,":[129],"as":[131,186],"Probabilistic-Latent":[132],"Semantic":[133],"Analysis,":[134],"or":[135],"Latent":[136],"Dirichlet":[137],"Allocation.":[138],"underlying":[140],"idea":[141],"we":[147],"collect":[148],"very":[150],"large":[151],"external":[152],"data":[153,180],"collection":[154],"\u201cuniversal":[156],"dataset,\u201d":[157],"then":[159],"build":[160],"both":[165],"original":[167],"rich":[171],"set":[172],"discovered":[176],"universal":[179],"collection.":[181],"can":[183,208],"seen":[185],"richer":[188],"representation":[189],"clustered.":[194],"We":[195],"carry":[196],"out":[197],"careful":[198],"evaluation":[199],"our":[201,206],"method":[202,207],"show":[204],"yield":[209],"impressive":[210],"quality.":[212]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
