{"id":"https://openalex.org/W2052896341","doi":"https://doi.org/10.1109/tkde.2014.2377727","title":"Probabilistic Word Selection via Topic Modeling","display_name":"Probabilistic Word Selection via Topic Modeling","publication_year":2015,"publication_date":"2015-01-06","ids":{"openalex":"https://openalex.org/W2052896341","doi":"https://doi.org/10.1109/tkde.2014.2377727","mag":"2052896341"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2014.2377727","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2014.2377727","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","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/A5008666077","display_name":"Yueting Zhuang","orcid":"https://orcid.org/0000-0001-9017-2508"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yueting Zhuang","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, No. 38, Zheda Road, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, No. 38, Zheda Road, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076008697","display_name":"Haidong Gao","orcid":"https://orcid.org/0000-0003-2774-5013"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haidong Gao","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, No. 38, Zheda Road, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, No. 38, Zheda Road, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004882141","display_name":"Fei Wu","orcid":"https://orcid.org/0000-0003-2139-8807"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Wu","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, No. 38, Zheda Road, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, No. 38, Zheda Road, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063062444","display_name":"Siliang Tang","orcid":"https://orcid.org/0000-0002-7356-9711"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siliang Tang","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, No. 38, Zheda Road, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, No. 38, Zheda Road, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100343699","display_name":"Yin Zhang","orcid":"https://orcid.org/0000-0001-6986-4227"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yin Zhang","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, No. 38, Zheda Road, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, No. 38, Zheda Road, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036747535","display_name":"Zhongfei Zhang","orcid":"https://orcid.org/0000-0001-5098-2506"},"institutions":[{"id":"https://openalex.org/I123946342","display_name":"Binghamton University","ror":"https://ror.org/008rmbt77","country_code":"US","type":"education","lineage":["https://openalex.org/I123946342"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhongfei Zhang","raw_affiliation_strings":["Department of Computer Science, State University of New York, Binghamton, NY","[Department of Computer Science, State University of New York, Binghamton, NY]"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, State University of New York, Binghamton, NY","institution_ids":["https://openalex.org/I123946342"]},{"raw_affiliation_string":"[Department of Computer Science, State University of New York, Binghamton, NY]","institution_ids":["https://openalex.org/I123946342"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5008666077"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":2.5886,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.91406842,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"27","issue":"6","first_page":"1643","last_page":"1655"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9994999766349792,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9972000122070312,"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":0.7857238054275513},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6894459128379822},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6773833632469177},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6598663330078125},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6386495232582092},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.6097143292427063},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.5958731174468994},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5364317297935486},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4723668694496155},{"id":"https://openalex.org/keywords/bernoulli-distribution","display_name":"Bernoulli distribution","score":0.4560343027114868},{"id":"https://openalex.org/keywords/bag-of-words-model","display_name":"Bag-of-words model","score":0.412082314491272},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3786590099334717},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15121519565582275},{"id":"https://openalex.org/keywords/random-variable","display_name":"Random variable","score":0.11015620827674866}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7857238054275513},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6894459128379822},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6773833632469177},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6598663330078125},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6386495232582092},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.6097143292427063},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.5958731174468994},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5364317297935486},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4723668694496155},{"id":"https://openalex.org/C27956954","wikidata":"https://www.wikidata.org/wiki/Q391371","display_name":"Bernoulli distribution","level":3,"score":0.4560343027114868},{"id":"https://openalex.org/C13672336","wikidata":"https://www.wikidata.org/wiki/Q3460803","display_name":"Bag-of-words model","level":2,"score":0.412082314491272},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3786590099334717},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15121519565582275},{"id":"https://openalex.org/C122123141","wikidata":"https://www.wikidata.org/wiki/Q176623","display_name":"Random variable","level":2,"score":0.11015620827674866},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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":1,"locations":[{"id":"doi:10.1109/tkde.2014.2377727","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2014.2377727","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7200000286102295,"id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G114879407","display_name":null,"funder_award_id":"CCF-1017828","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1722295131","display_name":null,"funder_award_id":"LQ14F010004","funder_id":"https://openalex.org/F4320338464","funder_display_name":"Natural Science Foundation of Zhejiang Province"},{"id":"https://openalex.org/G3535664698","display_name":null,"funder_award_id":"61402401","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G416067786","display_name":null,"funder_award_id":"61402403","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4192510761","display_name":null,"funder_award_id":"2012AA012505","funder_id":"https://openalex.org/F4320335773","funder_display_name":"National High-tech Research and Development Program"},{"id":"https://openalex.org/G5845502335","display_name":null,"funder_award_id":"LQ13F020001","funder_id":"https://openalex.org/F4320338464","funder_display_name":"Natural Science Foundation of Zhejiang Province"},{"id":"https://openalex.org/G8017731688","display_name":null,"funder_award_id":"2012CB316400","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309644","display_name":"State University of New York","ror":"https://ror.org/01q1z8k08"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335773","display_name":"National High-tech Research and Development Program","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320338464","display_name":"Natural Science Foundation of Zhejiang Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W1512098439","https://openalex.org/W1516111018","https://openalex.org/W1676494021","https://openalex.org/W1880262756","https://openalex.org/W1934021597","https://openalex.org/W1947594277","https://openalex.org/W1969486090","https://openalex.org/W2001082470","https://openalex.org/W2020842694","https://openalex.org/W2061806977","https://openalex.org/W2098062695","https://openalex.org/W2107008379","https://openalex.org/W2107034620","https://openalex.org/W2107743791","https://openalex.org/W2112050062","https://openalex.org/W2118020653","https://openalex.org/W2119650157","https://openalex.org/W2122683976","https://openalex.org/W2132827946","https://openalex.org/W2133568543","https://openalex.org/W2134731454","https://openalex.org/W2140124448","https://openalex.org/W2149684865","https://openalex.org/W2158266063","https://openalex.org/W2158698691","https://openalex.org/W2161050705","https://openalex.org/W2169289922","https://openalex.org/W2172085063","https://openalex.org/W2174706414","https://openalex.org/W2949169239","https://openalex.org/W2963214665","https://openalex.org/W2964291985","https://openalex.org/W4231510805","https://openalex.org/W4233135949","https://openalex.org/W4248892431","https://openalex.org/W4285719527","https://openalex.org/W4300448178","https://openalex.org/W6630527977","https://openalex.org/W6635817268","https://openalex.org/W6637028002","https://openalex.org/W6639619044","https://openalex.org/W6640231202","https://openalex.org/W6640753970","https://openalex.org/W6674735981","https://openalex.org/W6676132248","https://openalex.org/W6677859241","https://openalex.org/W6679439793","https://openalex.org/W6679607006","https://openalex.org/W6682304300","https://openalex.org/W6683603713","https://openalex.org/W6684927031","https://openalex.org/W6834357723","https://openalex.org/W7075742223"],"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/W3005513013","https://openalex.org/W2611137333","https://openalex.org/W4309228610","https://openalex.org/W2318387922"],"abstract_inverted_index":{"We":[0,21],"propose":[1],"selective":[2],"supervised":[3,17,106],"Latent":[4],"Dirichlet":[5],"Allocation":[6],"(ssLDA)":[7],"to":[8,33,45,96,196],"boost":[9],"the":[10,14,55,59,68,77,81,86,90,102,126,142,147,179,194,198,202,206],"prediction":[11],"performance":[12],"of":[13,58,76,105,115,128,155,188,201],"widely":[15],"studied":[16],"probabilistic":[18,78,183],"topic":[19,82],"models.":[20],"introduce":[22],"a":[23,37,66,73,98,119,152],"Bernoulli":[24,50],"distribution":[25,51],"for":[26,61,133,145],"each":[27],"word":[28,35,60,130],"in":[29,80,89,137,157,186,205],"one":[30,42],"given":[31],"document":[32,69,135],"selectthis":[34],"as":[36,72],"strongly":[38],"or":[39,85],"weakly":[40],"discriminative":[41],"with":[43,209],"respect":[44],"its":[46,62],"assigned":[47,63],"topic.":[48,64],"The":[49,159],"is":[52,70],"parameterized":[53],"by":[54,118],"discrimination":[56,199],"power":[57,200],"As":[65],"result,":[67],"represented":[71],"\u201cbag-of-selective-words\u201d":[74],"instead":[75],"\u201cbag-of-topics\u201d":[79,184],"modeling":[83],"domain":[84,95],"flat":[87,180],"\u201cbag-of-words\u201d":[88,181],"traditional":[91],"natural":[92],"language":[93],"processing":[94],"form":[97],"new":[99],"perspective.":[100],"Inheriting":[101],"general":[103],"framework":[104],"LDA":[107],"(sLDA),":[108],"ssLDA":[109,167],"can":[110],"also":[111,192],"predict":[112],"many":[113],"types":[114],"response":[116],"specified":[117,204],"Gaussian":[120],"Linear":[121],"Model":[122],"(GLM).":[123],"Focusing":[124],"on":[125,162,177],"utilization":[127],"this":[129,138],"selection":[131],"mechanism":[132],"singe-label":[134],"classification":[136,174,189],"paper,":[139],"we":[140],"conduct":[141],"variational":[143],"inference":[144],"approximating":[146],"intractable":[148],"posterior":[149],"and":[150,182],"derive":[151],"maximum-likelihood":[153],"estimation":[154],"parameters":[156],"ssLDA.":[158],"experiments":[160],"reported":[161],"textual":[163],"documents":[164],"show":[165],"that":[166],"not":[168],"only":[169],"performs":[170],"competitively":[171],"over":[172],"\u201cstate-of-the-art\u201d":[173],"approaches":[175],"based":[176],"both":[178],"representation":[185],"terms":[187],"performance,":[190],"but":[191],"has":[193],"ability":[195],"discover":[197],"words":[203],"topics":[207],"(compatible":[208],"our":[210],"rational":[211],"knowledge).":[212]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}