{"id":"https://openalex.org/W2516537890","doi":"https://doi.org/10.1145/2939672.2939880","title":"Topic Modeling of Short Texts","display_name":"Topic Modeling of Short Texts","publication_year":2016,"publication_date":"2016-08-08","ids":{"openalex":"https://openalex.org/W2516537890","doi":"https://doi.org/10.1145/2939672.2939880","mag":"2516537890"},"language":"en","primary_location":{"id":"doi:10.1145/2939672.2939880","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2939672.2939880","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","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/A5019690305","display_name":"Yuan Zuo","orcid":"https://orcid.org/0000-0001-8516-2567"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuan Zuo","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035293475","display_name":"Junjie Wu","orcid":"https://orcid.org/0000-0001-7650-3657"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junjie Wu","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100637526","display_name":"Hui Zhang","orcid":"https://orcid.org/0000-0002-2501-712X"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Zhang","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065918713","display_name":"Hao Lin","orcid":"https://orcid.org/0000-0002-1921-3036"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Lin","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100455805","display_name":"Fei Wang","orcid":"https://orcid.org/0000-0002-2212-3947"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Wang","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107234003","display_name":"Ke Xu","orcid":"https://orcid.org/0000-0001-5447-8008"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Xu","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101862104","display_name":"Hui Xiong","orcid":"https://orcid.org/0000-0001-6016-6465"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hui Xiong","raw_affiliation_strings":["Rutgers, the State University of New Jersey, Newark, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rutgers, the State University of New Jersey, Newark, USA","institution_ids":["https://openalex.org/I102322142"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5019690305"],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":24.7379,"has_fulltext":false,"cited_by_count":180,"citation_normalized_percentile":{"value":0.99492175,"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":"2105","last_page":"2114"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/T11550","display_name":"Text and Document Classification Technologies","score":0.9944999814033508,"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":0.9941999912261963,"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/topic-model","display_name":"Topic model","score":0.8382266163825989},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7894570827484131},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.7329169511795044},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5950387716293335},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5918038487434387},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.5171715617179871},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.45173296332359314},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.4442523121833801},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43414780497550964},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4211709499359131},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4145597219467163},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3644181191921234},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3226723074913025},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1498292088508606},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.09965780377388}],"concepts":[{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.8382266163825989},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7894570827484131},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7329169511795044},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5950387716293335},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5918038487434387},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.5171715617179871},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.45173296332359314},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.4442523121833801},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43414780497550964},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4211709499359131},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4145597219467163},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3644181191921234},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3226723074913025},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1498292088508606},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.09965780377388},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2939672.2939880","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2939672.2939880","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W159693449","https://openalex.org/W197049292","https://openalex.org/W1598801360","https://openalex.org/W1714665356","https://openalex.org/W1880262756","https://openalex.org/W1969415786","https://openalex.org/W2001082470","https://openalex.org/W2004192095","https://openalex.org/W2052261215","https://openalex.org/W2057587538","https://openalex.org/W2061922307","https://openalex.org/W2063904635","https://openalex.org/W2064772995","https://openalex.org/W2076219102","https://openalex.org/W2087743880","https://openalex.org/W2097089247","https://openalex.org/W2098047130","https://openalex.org/W2101318094","https://openalex.org/W2106490775","https://openalex.org/W2107743791","https://openalex.org/W2130339025","https://openalex.org/W2139317750","https://openalex.org/W2147946282","https://openalex.org/W2150731624","https://openalex.org/W2151703435","https://openalex.org/W2158266063","https://openalex.org/W2168332560","https://openalex.org/W2171343266","https://openalex.org/W2172135926","https://openalex.org/W2174706414","https://openalex.org/W2222893162","https://openalex.org/W2244191099","https://openalex.org/W2412709527","https://openalex.org/W2597289420","https://openalex.org/W2614207632","https://openalex.org/W4233135949"],"related_works":["https://openalex.org/W1574414179","https://openalex.org/W4362597605","https://openalex.org/W4297676672","https://openalex.org/W4281702477","https://openalex.org/W2922073769","https://openalex.org/W4378510483","https://openalex.org/W2768373660","https://openalex.org/W2073891040","https://openalex.org/W1968042686","https://openalex.org/W1510133244"],"abstract_inverted_index":{"Recent":[0],"years":[1],"have":[2,47],"witnessed":[3],"the":[4,16,24,63,91,130,145,184,207,238,248,264,278],"unprecedented":[5],"growth":[6],"of":[7,21,26,54,107,132,148,186,210,240,266,281],"online":[8],"social":[9],"media,":[10],"which":[11,62],"empower":[12],"short":[13,29,59,124,138,154,252],"texts":[14,139],"as":[15],"prevalent":[17],"format":[18],"for":[19,58,75,123,172,263,289],"information":[20,70],"Internet.":[22],"Given":[23],"nature":[25],"sparsity,":[27],"however,":[28],"text":[30,125,253],"topic":[31,56,126,146,290],"modeling":[32,144],"remains":[33],"a":[34,114,232,251],"critical":[35],"yet":[36],"much-watched":[37],"challenge":[38],"in":[39,109,163,284],"both":[40,164],"academy":[41],"and":[42,90,102,166,180,193,215,246],"industry.":[43],"Rich":[44],"research":[45],"efforts":[46],"been":[48],"put":[49],"on":[50,198],"building":[51],"different":[52],"types":[53],"probabilistic":[55,116],"models":[57,82],"texts,":[60,155],"among":[61],"self":[64],"aggregation":[65],"methods":[66],"without":[67],"using":[68],"auxiliary":[69],"become":[71],"an":[72,271],"emerging":[73],"solution":[74],"providing":[76],"informative":[77],"cross-text":[78,286],"word":[79,287],"co-occurrences.":[80],"However,":[81],"along":[83],"this":[84,110],"line":[85],"are":[86],"still":[87],"rarely":[88],"seen,":[89],"representative":[92],"one":[93,257],"Self-Aggregation":[94],"Topic":[95,120],"Model":[96,121],"(SATM)":[97],"is":[98,157,174,223,243,260],"prone":[99],"to":[100,135,159,226,255,275],"overfitting":[101],"computationally":[103],"expensive.":[104],"In":[105],"light":[106],"this,":[108],"paper,":[111],"we":[112],"propose":[113],"novel":[115],"model":[117],"called":[118],"Pseudo-document-based":[119],"(PTM)":[122],"modeling.":[127,291],"PTM":[128,156,170,214,236],"introduces":[129],"concept":[131],"pseudo":[133,150,191,241,258,282],"document":[134,259],"implicitly":[136],"aggregate":[137],"against":[140],"data":[141,201],"sparsity.":[142],"By":[143],"distributions":[147],"latent":[149,194],"documents":[151,192,242,283],"rather":[152],"than":[153],"expected":[158],"gain":[160],"excellent":[161],"performance":[162],"accuracy":[165],"efficiency.":[167],"A":[168],"Sparsity-enhanced":[169],"(SPTM":[171],"short)":[173],"also":[175,224],"proposed":[176],"by":[177,213],"applying":[178],"Spike":[179],"Slab":[181],"prior,":[182],"with":[183,203,218],"purpose":[185],"eliminating":[187],"undesired":[188],"correlations":[189],"between":[190],"topics.":[195],"Extensive":[196],"experiments":[197],"various":[199],"real-world":[200],"sets":[202],"state-of-the-art":[204],"baselines":[205],"demonstrate":[206],"high":[208],"quality":[209],"topics":[211],"learned":[212],"its":[216],"robustness":[217],"reduced":[219],"training":[220],"samples.":[221],"It":[222],"interesting":[225],"show":[227],"that":[228,250],"i)":[229],"SPTM":[230],"gains":[231],"clear":[233],"edge":[234],"over":[235],"when":[237],"number":[239],"relatively":[244],"small,":[245],"ii)":[247],"constraint":[249],"belongs":[254],"only":[256],"critically":[261],"important":[262],"success":[265],"PTM.":[267],"We":[268],"finally":[269],"take":[270],"in-depth":[272],"semantic":[273],"analysis":[274],"unveil":[276],"directly":[277],"fabulous":[279],"function":[280],"finding":[285],"co-occurrences":[288]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":22},{"year":2022,"cited_by_count":24},{"year":2021,"cited_by_count":26},{"year":2020,"cited_by_count":34},{"year":2019,"cited_by_count":19},{"year":2018,"cited_by_count":23},{"year":2017,"cited_by_count":13},{"year":2016,"cited_by_count":1}],"updated_date":"2026-06-03T09:05:47.796612","created_date":"2025-10-10T00:00:00"}