{"id":"https://openalex.org/W3021053579","doi":"https://doi.org/10.1109/tkde.2020.2992485","title":"Short Text Topic Modeling Techniques, Applications, and Performance: A Survey","display_name":"Short Text Topic Modeling Techniques, Applications, and Performance: A Survey","publication_year":2020,"publication_date":"2020-05-04","ids":{"openalex":"https://openalex.org/W3021053579","doi":"https://doi.org/10.1109/tkde.2020.2992485","mag":"3021053579"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2020.2992485","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2020.2992485","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/A5062724090","display_name":"Jipeng Qiang","orcid":"https://orcid.org/0000-0001-5721-0293"},"institutions":[{"id":"https://openalex.org/I78978612","display_name":"Yangzhou University","ror":"https://ror.org/03tqb8s11","country_code":"CN","type":"education","lineage":["https://openalex.org/I78978612"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jipeng Qiang","raw_affiliation_strings":["Department of Computer Science, Yangzhou University, Jiangsu, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Yangzhou University, Jiangsu, China","institution_ids":["https://openalex.org/I78978612"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101738812","display_name":"Zhenyu Qian","orcid":"https://orcid.org/0000-0003-4037-1976"},"institutions":[{"id":"https://openalex.org/I78978612","display_name":"Yangzhou University","ror":"https://ror.org/03tqb8s11","country_code":"CN","type":"education","lineage":["https://openalex.org/I78978612"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenyu Qian","raw_affiliation_strings":["Department of Computer Science, Yangzhou University, Jiangsu, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Yangzhou University, Jiangsu, China","institution_ids":["https://openalex.org/I78978612"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101793983","display_name":"Yun Li","orcid":"https://orcid.org/0000-0002-7628-0358"},"institutions":[{"id":"https://openalex.org/I78978612","display_name":"Yangzhou University","ror":"https://ror.org/03tqb8s11","country_code":"CN","type":"education","lineage":["https://openalex.org/I78978612"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun Li","raw_affiliation_strings":["Department of Computer Science, Yangzhou University, Jiangsu, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Yangzhou University, Jiangsu, China","institution_ids":["https://openalex.org/I78978612"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055757510","display_name":"Yunhao Yuan","orcid":"https://orcid.org/0000-0003-3712-443X"},"institutions":[{"id":"https://openalex.org/I78978612","display_name":"Yangzhou University","ror":"https://ror.org/03tqb8s11","country_code":"CN","type":"education","lineage":["https://openalex.org/I78978612"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunhao Yuan","raw_affiliation_strings":["Department of Computer Science, Yangzhou University, Jiangsu, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Yangzhou University, Jiangsu, China","institution_ids":["https://openalex.org/I78978612"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080738591","display_name":"Xindong Wu","orcid":"https://orcid.org/0000-0003-2396-1704"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xindong Wu","raw_affiliation_strings":["Key Laboratory of Knowledge Engineering with Big Data, Ministry of Education, Hefei University of Technology, Hefei, Anhui, China","Mininglamp Academy of Sciences, Minininglamp, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Knowledge Engineering with Big Data, Ministry of Education, Hefei University of Technology, Hefei, Anhui, China","institution_ids":["https://openalex.org/I16365422"]},{"raw_affiliation_string":"Mininglamp Academy of Sciences, Minininglamp, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5062724090"],"corresponding_institution_ids":["https://openalex.org/I78978612"],"apc_list":null,"apc_paid":null,"fwci":24.6016,"has_fulltext":false,"cited_by_count":299,"citation_normalized_percentile":{"value":0.99652987,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"34","issue":"3","first_page":"1427","last_page":"1445"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9972000122070312,"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"}},{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9961000084877014,"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":0.8820106983184814},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.8011162281036377},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.6968249082565308},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5626698136329651},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5248311161994934},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5231479406356812},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4858652949333191},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47832512855529785},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.45358824729919434},{"id":"https://openalex.org/keywords/probabilistic-latent-semantic-analysis","display_name":"Probabilistic latent semantic analysis","score":0.4346199333667755},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4091094434261322},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.34930509328842163}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8820106983184814},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.8011162281036377},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.6968249082565308},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5626698136329651},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5248311161994934},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5231479406356812},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4858652949333191},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47832512855529785},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.45358824729919434},{"id":"https://openalex.org/C112933361","wikidata":"https://www.wikidata.org/wiki/Q2845258","display_name":"Probabilistic latent semantic analysis","level":2,"score":0.4346199333667755},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4091094434261322},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.34930509328842163},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tkde.2020.2992485","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2020.2992485","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":[{"score":0.7200000286102295,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G1450990713","display_name":null,"funder_award_id":"91746209","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G325009246","display_name":null,"funder_award_id":"61703362","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5022471313","display_name":null,"funder_award_id":"BK20170513","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"},{"id":"https://openalex.org/G7297195451","display_name":null,"funder_award_id":"2016YFB1000900","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":75,"referenced_works":["https://openalex.org/W192243523","https://openalex.org/W232057064","https://openalex.org/W1989753615","https://openalex.org/W1989910872","https://openalex.org/W1993108184","https://openalex.org/W2003184546","https://openalex.org/W2004192095","https://openalex.org/W2048195127","https://openalex.org/W2051434435","https://openalex.org/W2053968437","https://openalex.org/W2056797132","https://openalex.org/W2061922307","https://openalex.org/W2063904635","https://openalex.org/W2064772995","https://openalex.org/W2066365352","https://openalex.org/W2076219102","https://openalex.org/W2090491854","https://openalex.org/W2097089247","https://openalex.org/W2097417931","https://openalex.org/W2099970131","https://openalex.org/W2123661878","https://openalex.org/W2127785456","https://openalex.org/W2137958601","https://openalex.org/W2139317750","https://openalex.org/W2151451758","https://openalex.org/W2151703435","https://openalex.org/W2160170318","https://openalex.org/W2162262658","https://openalex.org/W2166008115","https://openalex.org/W2168332560","https://openalex.org/W2171836785","https://openalex.org/W2174706414","https://openalex.org/W2178725228","https://openalex.org/W2197590357","https://openalex.org/W2232290562","https://openalex.org/W2250539671","https://openalex.org/W2251028926","https://openalex.org/W2258702405","https://openalex.org/W2296641297","https://openalex.org/W2328995640","https://openalex.org/W2340381866","https://openalex.org/W2380042537","https://openalex.org/W2404243041","https://openalex.org/W2438985978","https://openalex.org/W2511329098","https://openalex.org/W2516537890","https://openalex.org/W2573074123","https://openalex.org/W2586593666","https://openalex.org/W2605183993","https://openalex.org/W2745475103","https://openalex.org/W2750733752","https://openalex.org/W2761868254","https://openalex.org/W2788615138","https://openalex.org/W2808998506","https://openalex.org/W2963726741","https://openalex.org/W2964291985","https://openalex.org/W4233135949","https://openalex.org/W4237791300","https://openalex.org/W4244872530","https://openalex.org/W4293503257","https://openalex.org/W4299590111","https://openalex.org/W6601079536","https://openalex.org/W6635817268","https://openalex.org/W6674813771","https://openalex.org/W6677994088","https://openalex.org/W6679482899","https://openalex.org/W6680343917","https://openalex.org/W6682044806","https://openalex.org/W6682691769","https://openalex.org/W6683240801","https://openalex.org/W6683333316","https://openalex.org/W6684489972","https://openalex.org/W6689050917","https://openalex.org/W6691581006","https://openalex.org/W6764096679"],"related_works":["https://openalex.org/W1551384396","https://openalex.org/W2888805565","https://openalex.org/W2096865229","https://openalex.org/W2921491680","https://openalex.org/W2251863249","https://openalex.org/W4291700620","https://openalex.org/W2132052677","https://openalex.org/W3159709618","https://openalex.org/W4396666968","https://openalex.org/W2110027950"],"abstract_inverted_index":{"Analyzing":[0],"short":[1,24,56,59,86,98],"texts":[2],"infers":[3],"discriminative":[4],"and":[5,13,34,121,131,184,191],"coherent":[6],"latent":[7],"topics":[8],"that":[9,152],"is":[10,53],"a":[11,93,158],"critical":[12],"fundamental":[14],"task":[15],"since":[16,46],"many":[17,181],"real-world":[18,182],"applications":[19],"require":[20],"semantic":[21],"understanding":[22],"of":[23,83,96,111,125,133,167],"texts.":[25,57,87],"Traditional":[26],"long":[27,193],"text":[28,60,99,194],"topic":[29,61,100,195],"modeling":[30,62,101,196],"algorithms":[31,156],"(e.g.,":[32],"PLSA":[33],"LDA)":[35],"based":[36,113],"on":[37,114,136,180],"word":[38,50,119],"co-occurrences":[39],"cannot":[40],"solve":[41],"this":[42,89,171],"problem":[43,82],"very":[44,48],"well":[45],"only":[47],"limited":[49],"co-occurrence":[51],"information":[52],"available":[54],"in":[55,74,85,104,128,150,170],"Therefore,":[58],"has":[63],"already":[64],"attracted":[65],"much":[66],"attention":[67],"from":[68],"the":[69,81,105,141,165],"machine":[70],"learning":[71],"research":[72,172],"community":[73],"recent":[75],"years,":[76],"which":[77],"aims":[78],"at":[79],"overcoming":[80],"sparseness":[84],"In":[88],"survey,":[90],"we":[91,175],"conduct":[92],"comprehensive":[94,143],"review":[95],"various":[97,137],"techniques":[102],"proposed":[103],"literature.":[106],"We":[107,139],"present":[108],"three":[109],"categories":[110],"methods":[112,169,179],"Dirichlet":[115],"multinomial":[116],"mixture,":[117],"global":[118],"co-occurrences,":[120],"self-aggregation,":[122],"with":[123],"example":[124],"representative":[126],"approaches":[127],"each":[129],"category":[130],"analysis":[132],"their":[134,186],"performance":[135,187],"tasks.":[138],"develop":[140],"first":[142],"open-source":[144],"library,":[145],"called":[146],"STTM,":[147],"for":[148],"use":[149],"Java":[151],"integrates":[153],"all":[154],"surveyed":[155],"within":[157],"unified":[159],"interface,":[160],"benchmark":[161],"datasets,":[162],"to":[163],"facilitate":[164],"expansion":[166],"new":[168],"field.":[173],"Finally,":[174],"evaluate":[176],"these":[177],"state-of-the-art":[178],"datasets":[183],"compare":[185],"against":[188],"one":[189],"another":[190],"versus":[192],"algorithm.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":44},{"year":2024,"cited_by_count":65},{"year":2023,"cited_by_count":61},{"year":2022,"cited_by_count":60},{"year":2021,"cited_by_count":46},{"year":2020,"cited_by_count":14}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}