{"id":"https://openalex.org/W2788615138","doi":"https://doi.org/10.1145/3178876.3186009","title":"Short-Text Topic Modeling via Non-negative Matrix Factorization Enriched with Local Word-Context Correlations","display_name":"Short-Text Topic Modeling via Non-negative Matrix Factorization Enriched with Local Word-Context Correlations","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2788615138","doi":"https://doi.org/10.1145/3178876.3186009","mag":"2788615138"},"language":"en","primary_location":{"id":"doi:10.1145/3178876.3186009","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3178876.3186009","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3186009&type=pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 World Wide Web Conference on World Wide Web - WWW '18","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dl.acm.org/ft_gateway.cfm?id=3186009&type=pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019616632","display_name":"Tian Shi","orcid":"https://orcid.org/0000-0002-7604-5665"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tian Shi","raw_affiliation_strings":["Virginia Tech, Arlington, VA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Virginia Tech, Arlington, VA, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032506972","display_name":"Kyeongpil Kang","orcid":null},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyeongpil Kang","raw_affiliation_strings":["Korea University, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University, Seoul, South Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047912015","display_name":"Jaegul Choo","orcid":"https://orcid.org/0000-0003-1071-4835"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaegul Choo","raw_affiliation_strings":["Korea University, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University, Seoul, South Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001022750","display_name":"Chandan K. Reddy","orcid":"https://orcid.org/0000-0003-2839-3662"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chandan K. Reddy","raw_affiliation_strings":["Virginia Tech, Arlington, VA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Virginia Tech, Arlington, VA, USA","institution_ids":["https://openalex.org/I859038795"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":14.8681,"has_fulltext":true,"cited_by_count":175,"citation_normalized_percentile":{"value":0.99050469,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1105","last_page":"1114"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9984999895095825,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9984999895095825,"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/interpretability","display_name":"Interpretability","score":0.8469600677490234},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8258688449859619},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6114444732666016},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5998702049255371},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5538924932479858},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5317664742469788},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.49714162945747375},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.4937804639339447},{"id":"https://openalex.org/keywords/word2vec","display_name":"Word2vec","score":0.4888758063316345},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4777054786682129},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.4539993107318878},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.35196182131767273},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10271531343460083}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8469600677490234},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8258688449859619},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6114444732666016},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5998702049255371},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5538924932479858},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5317664742469788},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.49714162945747375},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.4937804639339447},{"id":"https://openalex.org/C2776461190","wikidata":"https://www.wikidata.org/wiki/Q22673982","display_name":"Word2vec","level":3,"score":0.4888758063316345},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4777054786682129},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.4539993107318878},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35196182131767273},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10271531343460083},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3178876.3186009","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3178876.3186009","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3186009&type=pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 World Wide Web Conference on World Wide Web - WWW '18","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3178876.3186009","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3178876.3186009","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3186009&type=pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 World Wide Web Conference on World Wide Web - WWW '18","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4099999964237213}],"awards":[{"id":"https://openalex.org/G2037717774","display_name":"III: Small: Collaborative Research: Global Event and Trend Archive Research (GETAR)","funder_award_id":"1619028","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2690932125","display_name":null,"funder_award_id":"IIS-1707498","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3223590597","display_name":null,"funder_award_id":"IIS-1619028","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3343279563","display_name":"III: Small: New Machine Learning Approaches for Modeling Time-to-Event Data","funder_award_id":"1707498","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5743301901","display_name":null,"funder_award_id":"IIS-1646881","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7540830453","display_name":null,"funder_award_id":"NRF-2016R1C1B2015924","funder_id":"https://openalex.org/F4320322030","funder_display_name":"Ministry of Science, ICT and Future Planning"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322030","display_name":"Ministry of Science, ICT and Future Planning","ror":"https://ror.org/032e49973"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2788615138.pdf","grobid_xml":"https://content.openalex.org/works/W2788615138.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W33249699","https://openalex.org/W197049292","https://openalex.org/W1246381107","https://openalex.org/W1504886279","https://openalex.org/W1614298861","https://openalex.org/W1615991656","https://openalex.org/W1714665356","https://openalex.org/W1880262756","https://openalex.org/W1902027874","https://openalex.org/W2053968437","https://openalex.org/W2057990742","https://openalex.org/W2063904635","https://openalex.org/W2067931421","https://openalex.org/W2087382273","https://openalex.org/W2107743791","https://openalex.org/W2118585731","https://openalex.org/W2125031621","https://openalex.org/W2144351558","https://openalex.org/W2147152072","https://openalex.org/W2150594776","https://openalex.org/W2153579005","https://openalex.org/W2168332560","https://openalex.org/W2222893162","https://openalex.org/W2250539671","https://openalex.org/W2252172130","https://openalex.org/W2340381866","https://openalex.org/W2404400936","https://openalex.org/W2405765071","https://openalex.org/W2516537890","https://openalex.org/W2585828887","https://openalex.org/W3088066054","https://openalex.org/W4233135949"],"related_works":["https://openalex.org/W2905433371","https://openalex.org/W2888392564","https://openalex.org/W4310278675","https://openalex.org/W4388422664","https://openalex.org/W4390569940","https://openalex.org/W4361193272","https://openalex.org/W2963326959","https://openalex.org/W4388685194","https://openalex.org/W4312407344","https://openalex.org/W2894289927"],"abstract_inverted_index":{"Being":[0],"a":[1,23,36,67,116,124,134,185],"prevalent":[2],"form":[3],"of":[4,11,25,107,127,151,162,175],"social":[5],"communications":[6],"on":[7,141],"the":[8,78,84,89,92,96,104,108,128,148,152,173,189],"Internet,":[9],"billions":[10],"short":[12,33,79,144,201],"texts":[13,34],"are":[14,42,101],"generated":[15],"everyday.":[16],"Discovering":[17],"knowledge":[18],"from":[19,27,52,103],"them":[20,53],"has":[21],"gained":[22],"lot":[24],"interest":[26],"both":[28],"industry":[29],"and":[30,40,45,47,98,165,181,188],"academia.":[31],"The":[32,110,168],"have":[35],"limited":[37],"contextual":[38],"information,":[39],"they":[41],"sparse,":[43],"noisy":[44],"ambiguous,":[46],"hence,":[48],"automatically":[49],"learning":[50],"topics":[51,76],"remains":[54],"an":[55,195],"important":[56],"challenge.":[57],"To":[58],"tackle":[59],"this":[60,63],"problem,":[61],"in":[62,160],"paper,":[64],"we":[65],"propose":[66],"semantics-assisted":[68],"non-negative":[69],"matrix":[70],"factorization":[71],"(SeaNMF)":[72],"model":[73,112,130,136,199],"to":[74],"discover":[75],"for":[77,200],"texts.":[80,202],"It":[81],"effectively":[82],"incorporates":[83],"word-context":[85],"semantic":[86,93,170],"correlations":[87],"into":[88],"model,":[90],"where":[91],"relationships":[94],"between":[95],"words":[97],"their":[99],"contexts":[100],"learned":[102],"skip-gram":[105],"view":[106],"corpus.":[109],"SeaNMF":[111,129,192],"is":[113],"solved":[114],"using":[115],"block":[117],"coordinate":[118],"descent":[119],"algorithm.":[120],"We":[121],"also":[122],"develop":[123],"sparse":[125],"variant":[126],"which":[131],"can":[132,193],"achieve":[133],"better":[135],"interpretability.":[137],"Extensive":[138],"quantitative":[139],"evaluations":[140],"various":[142],"real-world":[143],"text":[145],"datasets":[146],"demonstrate":[147],"superior":[149,190],"performance":[150],"proposed":[153],"models":[154,177],"over":[155],"several":[156],"other":[157],"state-of-the-art":[158],"methods":[159],"terms":[161],"topic":[163,198],"coherence":[164],"classification":[166],"accuracy.":[167],"qualitative":[169],"analysis":[171],"demonstrates":[172],"interpretability":[174],"our":[176],"by":[178],"discovering":[179],"meaningful":[180],"consistent":[182],"topics.":[183],"With":[184],"simple":[186],"formulation":[187],"performance,":[191],"be":[194],"effective":[196],"standard":[197]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":19},{"year":2023,"cited_by_count":25},{"year":2022,"cited_by_count":32},{"year":2021,"cited_by_count":33},{"year":2020,"cited_by_count":33},{"year":2019,"cited_by_count":21},{"year":2018,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}