{"id":"https://openalex.org/W3201290210","doi":"https://doi.org/10.1109/access.2021.3113320","title":"A Pitman-Yor Process Self-Aggregated Topic Model for Short Texts of Social Media","display_name":"A Pitman-Yor Process Self-Aggregated Topic Model for Short Texts of Social Media","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3201290210","doi":"https://doi.org/10.1109/access.2021.3113320","mag":"3201290210"},"language":"en","primary_location":{"id":"doi:10.1109/access.2021.3113320","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3113320","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09540607.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09540607.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101472380","display_name":"Yue Niu","orcid":"https://orcid.org/0000-0002-1663-2921"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Niu","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China, Anhui, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-1663-2921","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China, Anhui, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100449658","display_name":"Hongjie Zhang","orcid":"https://orcid.org/0000-0001-9565-3378"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongjie Zhang","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China, Anhui, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China, Anhui, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100763409","display_name":"Jing Li","orcid":"https://orcid.org/0000-0001-6761-7687"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Li","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China, Anhui, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-6761-7687","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China, Anhui, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.6995,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.76667877,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"9","issue":null,"first_page":"129011","last_page":"129021"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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":0.9921000003814697,"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":0.9890000224113464,"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":0.8216809034347534},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.7108041644096375},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.6094996333122253},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5621818900108337},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.5225976705551147},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5224458575248718},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.5055408477783203},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.500899076461792},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.49592217803001404},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4829903841018677},{"id":"https://openalex.org/keywords/latent-semantic-analysis","display_name":"Latent semantic analysis","score":0.43233463168144226},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.39493727684020996},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.21333414316177368},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.156136155128479}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8216809034347534},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.7108041644096375},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.6094996333122253},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5621818900108337},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.5225976705551147},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5224458575248718},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.5055408477783203},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.500899076461792},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.49592217803001404},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4829903841018677},{"id":"https://openalex.org/C170133592","wikidata":"https://www.wikidata.org/wiki/Q1806883","display_name":"Latent semantic analysis","level":2,"score":0.43233463168144226},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39493727684020996},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.21333414316177368},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.156136155128479},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2021.3113320","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3113320","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09540607.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:106641ebcfff4322a763031e3e5c9157","is_oa":true,"landing_page_url":"https://doaj.org/article/106641ebcfff4322a763031e3e5c9157","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 9, Pp 129011-129021 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2021.3113320","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3113320","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09540607.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6499999761581421,"id":"https://metadata.un.org/sdg/1","display_name":"No poverty"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3201290210.pdf","grobid_xml":"https://content.openalex.org/works/W3201290210.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W1614298861","https://openalex.org/W1680392829","https://openalex.org/W1880262756","https://openalex.org/W1969415786","https://openalex.org/W1992440927","https://openalex.org/W2001082470","https://openalex.org/W2004192095","https://openalex.org/W2008056655","https://openalex.org/W2048195127","https://openalex.org/W2057587538","https://openalex.org/W2061922307","https://openalex.org/W2063904635","https://openalex.org/W2064772995","https://openalex.org/W2076219102","https://openalex.org/W2097089247","https://openalex.org/W2097417931","https://openalex.org/W2147946282","https://openalex.org/W2151703435","https://openalex.org/W2158266063","https://openalex.org/W2168332560","https://openalex.org/W2171343266","https://openalex.org/W2171836785","https://openalex.org/W2174706414","https://openalex.org/W2178725228","https://openalex.org/W2222893162","https://openalex.org/W2250753706","https://openalex.org/W2340381866","https://openalex.org/W2511329098","https://openalex.org/W2516537890","https://openalex.org/W2745475103","https://openalex.org/W2788615138","https://openalex.org/W2888777359","https://openalex.org/W2950133940","https://openalex.org/W2950577311","https://openalex.org/W2963593575","https://openalex.org/W2963726741","https://openalex.org/W2969961168","https://openalex.org/W3005792683","https://openalex.org/W3032414079","https://openalex.org/W3154475157","https://openalex.org/W4244872530","https://openalex.org/W4294170691","https://openalex.org/W6636510571","https://openalex.org/W6637386731","https://openalex.org/W6639619044","https://openalex.org/W6682044806","https://openalex.org/W6682691769","https://openalex.org/W6689050917","https://openalex.org/W6690901545","https://openalex.org/W6824062597"],"related_works":["https://openalex.org/W2921491680","https://openalex.org/W2995939990","https://openalex.org/W2996839460","https://openalex.org/W4297006557","https://openalex.org/W2171515436","https://openalex.org/W2981074787","https://openalex.org/W2914864478","https://openalex.org/W4390916997","https://openalex.org/W2474958513","https://openalex.org/W4313119814"],"abstract_inverted_index":{"In":[0,113],"recent":[1],"years,":[2],"with":[3,205,227],"the":[4,17,21,80,90,119,126,133,179,228],"rapid":[5],"growth":[6],"of":[7,24,34,82,128,135,230],"social":[8,196],"media,":[9],"short":[10,26,52,64,136,168,182,212],"texts":[11,65,169,183,213],"have":[12,73],"been":[13],"very":[14],"prevalent":[15],"on":[16,42,51,209],"internet.":[18],"Due":[19],"to":[20,47,94,123,132,139,166,224],"limited":[22],"length":[23],"each":[25],"text,":[27],"word":[28,43,107,142],"co-occurrence":[29,44,108],"information":[30],"in":[31,154,195],"this":[32,114],"type":[33],"documents":[35,84,103,130,153,186],"is":[36,57,78,99],"sparse.":[37],"Conventional":[38],"topic":[39,59,231],"models":[40,60,72],"based":[41],"are":[45],"unable":[46],"distill":[48],"coherent":[49],"topics":[50],"texts.":[53,137],"A":[54],"state-of-the-art":[55,207],"strategy":[56],"self-aggregated":[58],"which":[61,109,191],"implicitly":[62],"aggregate":[63,167],"into":[66,170],"latent":[67,101,151],"long":[68,83,102,129,152,171,185],"documents.":[69,172],"But":[70],"these":[71],"two":[74],"problems.":[75],"One":[76],"problem":[77,98],"that":[79,100,178,219],"number":[81,92,127],"should":[85],"be":[86,193],"defined":[87],"explicitly":[88],"and":[89,184,233],"inappropriate":[91],"leads":[93],"poor":[95],"performance.":[96],"Another":[97],"may":[104],"bring":[105],"non-sematic":[106],"brings":[110],"incoherent":[111],"topics.":[112],"article,":[115],"we":[116,144,201],"firstly":[117],"apply":[118],"Chinese":[120],"restaurant":[121],"process":[122,165,175],"automatically":[124],"generate":[125],"according":[131],"scale":[134],"Then":[138],"exclude":[140],"non-semantic":[141],"co-occurrence,":[143],"propose":[145],"a":[146,155,163,188],"novel":[147],"probabilistic":[148],"model":[149,161,221],"generating":[150],"more":[156],"semantically":[157],"way.":[158],"Specifically,":[159],"our":[160,203,220],"employs":[162],"pitman-yor":[164],"This":[173],"stochastic":[174],"can":[176,192],"guarantee":[177],"distribution":[180,190],"between":[181],"following":[187],"power-law":[189],"found":[194],"media":[197],"like":[198],"Twitter.":[199],"Finally,":[200],"compared":[202],"method":[204],"several":[206],"methods":[208,226],"four":[210],"real":[211],"corpus.":[214],"The":[215],"experiment":[216],"results":[217],"show":[218],"performs":[222],"superior":[223],"other":[225],"metrics":[229],"coherence":[232],"text":[234],"classification.":[235]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}