{"id":"https://openalex.org/W2171836785","doi":"https://doi.org/10.1145/1367497.1367510","title":"Learning to classify short and sparse text & web with hidden topics from large-scale data collections","display_name":"Learning to classify short and sparse text & web with hidden topics from large-scale data collections","publication_year":2008,"publication_date":"2008-04-21","ids":{"openalex":"https://openalex.org/W2171836785","doi":"https://doi.org/10.1145/1367497.1367510","mag":"2171836785"},"language":"en","primary_location":{"id":"doi:10.1145/1367497.1367510","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1367497.1367510","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th international conference on World Wide Web","raw_type":"proceedings-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/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, Sendai, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tohoku University, Sendai, Japan","institution_ids":["https://openalex.org/I201537933"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077641909","display_name":"Le-Minh Nguyen","orcid":"https://orcid.org/0000-0002-2265-1010"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Le-Minh Nguyen","raw_affiliation_strings":["Japan Advanced Institute of Science and Technology, Nomi, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology, Nomi, Japan","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"last","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, Sendai, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tohoku University, Sendai, Japan","institution_ids":["https://openalex.org/I201537933"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":42.3221,"has_fulltext":false,"cited_by_count":747,"citation_normalized_percentile":{"value":0.99836856,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"91","last_page":"100"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9986000061035156,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9986000061035156,"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/T10028","display_name":"Topic Modeling","score":0.9977999925613403,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9937000274658203,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7046533823013306},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.563129723072052},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3964172601699829},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3563976585865021},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.06619560718536377}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7046533823013306},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.563129723072052},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3964172601699829},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3563976585865021},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.06619560718536377},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1367497.1367510","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1367497.1367510","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th international conference on World Wide Web","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6299999952316284,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1536860849","https://openalex.org/W1573190978","https://openalex.org/W1646006088","https://openalex.org/W1730404227","https://openalex.org/W1790954942","https://openalex.org/W1880262756","https://openalex.org/W1996852448","https://openalex.org/W2001082470","https://openalex.org/W2020999234","https://openalex.org/W2042980227","https://openalex.org/W2045117606","https://openalex.org/W2048679005","https://openalex.org/W2049455633","https://openalex.org/W2051434435","https://openalex.org/W2064580901","https://openalex.org/W2088314245","https://openalex.org/W2096175520","https://openalex.org/W2097089247","https://openalex.org/W2104924585","https://openalex.org/W2110441437","https://openalex.org/W2110591510","https://openalex.org/W2118020653","https://openalex.org/W2120779048","https://openalex.org/W2121996546","https://openalex.org/W2128925311","https://openalex.org/W2132024321","https://openalex.org/W2135194391","https://openalex.org/W2141734078","https://openalex.org/W2147152072","https://openalex.org/W2149393279","https://openalex.org/W2149684865","https://openalex.org/W2160799467","https://openalex.org/W2161443453","https://openalex.org/W2997501009","https://openalex.org/W3012199806","https://openalex.org/W3099640513","https://openalex.org/W3158101117","https://openalex.org/W6634191187","https://openalex.org/W6676781583"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2530322880","https://openalex.org/W1596801655","https://openalex.org/W2359140296"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,123,134,138,146,181],"general":[4,160],"framework":[5,114,158],"for":[6,117,206],"building":[7],"classifiers":[8,103],"that":[9,38,116,154],"deal":[10],"with":[11,43,83,196],"short":[12,44],"and":[13,64,131,145,169,192,203,209],"sparse":[14],"text":[15,47],"&":[16,48,55,59,66],"Web":[199],"segments":[18,45],"by":[19],"making":[20],"the":[21,76,92,100,113],"most":[22],"of":[23,34,46,86,102,112,141,149,188],"hidden":[24,150],"topics":[25,151],"discovered":[26,152],"from":[27,153,172],"large-scale":[28,124],"data":[29,77,93,107,126,144,155,167],"collections.":[30],"The":[31,109,157],"main":[32],"motivation":[33],"this":[35],"work":[36],"is":[37,115,159],"many":[39],"classification":[40,119],"tasks":[41],"working":[42],"Web,":[49],"such":[50],"as":[51,96,98],"search":[52,174,200],"snippets,":[53],"forum":[54],"chat":[56],"messages,":[57],"blog":[58],"news":[60],"feeds,":[61],"product":[62],"reviews,":[63],"book":[65],"movie":[67],"summaries,":[68],"fail":[69],"to":[70,75,90,104,162,165,176],"achieve":[71],"high":[72],"accuracy":[73],"due":[74],"sparseness.":[78],"We,":[79],"therefore,":[80],"come":[81],"up":[82],"an":[84],"idea":[85,111],"gaining":[87],"external":[88,125],"knowledge":[89],"make":[91],"more":[94],"related":[95],"well":[97],"expand":[99],"coverage":[101],"handle":[105],"future":[106],"better.":[108],"underlying":[110],"each":[118],"task,":[120],"we":[121],"collect":[122],"collection":[127],"called":[128],"universal":[129],"dataset,":[130],"then":[132],"build":[133],"classifier":[135],"on":[136,184],"both":[137],"(small)":[139],"set":[140,148],"labeled":[142],"training":[143],"rich":[147],"collection.":[156],"enough":[161],"be":[163],"applied":[164],"different":[166],"domains":[168],"genres":[170],"ranging":[171],"results":[175],"medical":[177,207],"text.":[178],"We":[179],"did":[180],"careful":[182],"evaluation":[183],"several":[185],"hundred":[186],"megabytes":[187],"Wikipedia":[189],"(30M":[190],"words)":[191,195],"MEDLINE":[193],"(18M":[194],"two":[197],"tasks:":[198],"domain":[201],"disambiguation":[202],"disease":[204],"categorization":[205],"text,":[208],"achieved":[210],"significant":[211],"quality":[212],"enhancement.":[213]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":19},{"year":2023,"cited_by_count":31},{"year":2022,"cited_by_count":40},{"year":2021,"cited_by_count":44},{"year":2020,"cited_by_count":50},{"year":2019,"cited_by_count":51},{"year":2018,"cited_by_count":70},{"year":2017,"cited_by_count":66},{"year":2016,"cited_by_count":64},{"year":2015,"cited_by_count":62},{"year":2014,"cited_by_count":61},{"year":2013,"cited_by_count":55},{"year":2012,"cited_by_count":39}],"updated_date":"2026-06-24T13:16:06.693445","created_date":"2025-10-10T00:00:00"}