{"id":"https://openalex.org/W7221849385","doi":"https://doi.org/10.5753/kdmile.2026.31693","title":"Classical Tricks for Better Topics: Can Traditional Text Mining Techniques Improve Generative Topic Modeling?","display_name":"Classical Tricks for Better Topics: Can Traditional Text Mining Techniques Improve Generative Topic Modeling?","publication_year":2026,"publication_date":"2026-10-15","ids":{"openalex":"https://openalex.org/W7221849385","doi":"https://doi.org/10.5753/kdmile.2026.31693"},"language":"en","primary_location":{"id":"doi:10.5753/kdmile.2026.31693","doi":"https://doi.org/10.5753/kdmile.2026.31693","is_oa":true,"landing_page_url":"https://doi.org/10.5753/kdmile.2026.31693","pdf_url":"https://sol.sbc.org.br/index.php/kdmile/article/download/44973/44736","source":{"id":"https://openalex.org/S7407067392","display_name":"Anais do Symposium on Knowledge Discovery, Mining and Learning (KDMiLe)","issn_l":"2763-8944","issn":["2763-8944"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310312150","host_organization_name":"Brazilian Computer Society","host_organization_lineage":["https://openalex.org/P4310312150"],"host_organization_lineage_names":["Brazilian Computer Society"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Anais do XIV Symposium on Knowledge Discovery, Mining and Learning (KDMiLe 2026)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://sol.sbc.org.br/index.php/kdmile/article/download/44973/44736","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030260888","display_name":"Isis Meira","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I161127581","display_name":"Universidade Federal Fluminense","ror":"https://ror.org/02rjhbb08","country_code":"BR","type":"education","lineage":["https://openalex.org/I161127581"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Isis Meira","raw_affiliation_strings":["UFF"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UFF","institution_ids":["https://openalex.org/I161127581"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120151344","display_name":"Isabella Leite","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I161127581","display_name":"Universidade Federal Fluminense","ror":"https://ror.org/02rjhbb08","country_code":"BR","type":"education","lineage":["https://openalex.org/I161127581"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Isabella Leite","raw_affiliation_strings":["UFF"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UFF","institution_ids":["https://openalex.org/I161127581"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115064680","display_name":"Gabriel Assis","orcid":"https://orcid.org/0009-0000-2674-0427","observed_orcids":["https://orcid.org/0009-0000-2674-0427"]},"institutions":[{"id":"https://openalex.org/I161127581","display_name":"Universidade Federal Fluminense","ror":"https://ror.org/02rjhbb08","country_code":"BR","type":"education","lineage":["https://openalex.org/I161127581"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Gabriel Assis","raw_affiliation_strings":["UFF"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UFF","institution_ids":["https://openalex.org/I161127581"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5158783753","display_name":"Marcela Aniceto","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marcela Aniceto","raw_affiliation_strings":["Instituto de Ci\u00eancia e Tecnologia Ita\u00fa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Instituto de Ci\u00eancia e Tecnologia Ita\u00fa","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016328033","display_name":"Darian Soheil Rahnamaye Rabbani","orcid":"https://orcid.org/0000-0002-9045-1563","observed_orcids":["https://orcid.org/0000-0002-9045-1563"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Darian Rabbani","raw_affiliation_strings":["Instituto de Ci\u00eancia e Tecnologia Ita\u00fa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Instituto de Ci\u00eancia e Tecnologia Ita\u00fa","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038120583","display_name":"Lucas Francisco Amaral Orosco Pellicer","orcid":"https://orcid.org/0000-0003-2827-7602","observed_orcids":["https://orcid.org/0000-0003-2827-7602"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lucas Pellicer","raw_affiliation_strings":["Instituto de Ci\u00eancia e Tecnologia Ita\u00fa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Instituto de Ci\u00eancia e Tecnologia Ita\u00fa","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045549996","display_name":"Aline Paes","orcid":"https://orcid.org/0000-0002-9089-7303","observed_orcids":["https://orcid.org/0000-0002-9089-7303"]},"institutions":[{"id":"https://openalex.org/I161127581","display_name":"Universidade Federal Fluminense","ror":"https://ror.org/02rjhbb08","country_code":"BR","type":"education","lineage":["https://openalex.org/I161127581"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Aline Paes","raw_affiliation_strings":["UFF"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UFF","institution_ids":["https://openalex.org/I161127581"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.84530462,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"81","last_page":"88"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9818999767303467,"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":0.9818999767303467,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.01679999940097332,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.0003000000142492354,"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/document-selection","display_name":"document selection","score":0.6439999938011169},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.6940000057220459},{"id":"https://openalex.org/keywords/topic-labeling","display_name":"topic labeling","score":0.39399999380111694},{"id":"https://openalex.org/keywords/bertopic","display_name":"BERTopic","score":0.6420000195503235},{"id":"https://openalex.org/keywords/document-clustering","display_name":"document clustering","score":0.6449999809265137}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8008999824523926},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6945000290870667},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.6801999807357788},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6004999876022339},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5895000100135803},{"id":"https://openalex.org/C37381756","wikidata":"https://www.wikidata.org/wiki/Q20203288","display_name":"Representativeness heuristic","level":2,"score":0.5709999799728394},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.557200014591217},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5453000068664551},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42829999327659607},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4000000059604645},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.39820000529289246},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3837999999523163},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37389999628067017},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3472999930381775},{"id":"https://openalex.org/C2985684807","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Text generation","level":2,"score":0.33629998564720154},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3181000053882599},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.2996000051498413},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.2768000066280365},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.26899999380111694},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C2777946921","wikidata":"https://www.wikidata.org/wiki/Q7449044","display_name":"Semantic analysis (machine learning)","level":2,"score":0.26669999957084656}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5753/kdmile.2026.31693","doi":"https://doi.org/10.5753/kdmile.2026.31693","is_oa":true,"landing_page_url":"https://doi.org/10.5753/kdmile.2026.31693","pdf_url":"https://sol.sbc.org.br/index.php/kdmile/article/download/44973/44736","source":{"id":"https://openalex.org/S7407067392","display_name":"Anais do Symposium on Knowledge Discovery, Mining and Learning (KDMiLe)","issn_l":"2763-8944","issn":["2763-8944"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310312150","host_organization_name":"Brazilian Computer Society","host_organization_lineage":["https://openalex.org/P4310312150"],"host_organization_lineage_names":["Brazilian Computer Society"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Anais do XIV Symposium on Knowledge Discovery, Mining and Learning (KDMiLe 2026)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.5753/kdmile.2026.31693","doi":"https://doi.org/10.5753/kdmile.2026.31693","is_oa":true,"landing_page_url":"https://doi.org/10.5753/kdmile.2026.31693","pdf_url":"https://sol.sbc.org.br/index.php/kdmile/article/download/44973/44736","source":{"id":"https://openalex.org/S7407067392","display_name":"Anais do Symposium on Knowledge Discovery, Mining and Learning (KDMiLe)","issn_l":"2763-8944","issn":["2763-8944"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310312150","host_organization_name":"Brazilian Computer Society","host_organization_lineage":["https://openalex.org/P4310312150"],"host_organization_lineage_names":["Brazilian Computer Society"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Anais do XIV Symposium on Knowledge Discovery, Mining and Learning (KDMiLe 2026)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1207375514","display_name":null,"funder_award_id":"Code 001","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"},{"id":"https://openalex.org/G1743900142","display_name":null,"funder_award_id":"SEI-260003/002930/2024","funder_id":"https://openalex.org/F4320322749","funder_display_name":"Funda\u00e7\u00e3o Carlos Chagas Filho de Amparo \u00e0 Pesquisa do Estado do Rio de Janeiro"},{"id":"https://openalex.org/G2100037517","display_name":null,"funder_award_id":"SEI-260003/000614/2023","funder_id":"https://openalex.org/F4320322749","funder_display_name":"Funda\u00e7\u00e3o Carlos Chagas Filho de Amparo \u00e0 Pesquisa do Estado do Rio de Janeiro"},{"id":"https://openalex.org/G2447600711","display_name":null,"funder_award_id":"260003/002930/2024","funder_id":"https://openalex.org/F4320322749","funder_display_name":"Funda\u00e7\u00e3o Carlos Chagas Filho de Amparo \u00e0 Pesquisa do Estado do Rio de Janeiro"},{"id":"https://openalex.org/G3315780251","display_name":null,"funder_award_id":"SEI-260003","funder_id":"https://openalex.org/F4320322749","funder_display_name":"Funda\u00e7\u00e3o Carlos Chagas Filho de Amparo \u00e0 Pesquisa do Estado do Rio de Janeiro"},{"id":"https://openalex.org/G5395565924","display_name":null,"funder_award_id":"260003/000614/2023","funder_id":"https://openalex.org/F4320322749","funder_display_name":"Funda\u00e7\u00e3o Carlos Chagas Filho de Amparo \u00e0 Pesquisa do Estado do Rio de Janeiro"},{"id":"https://openalex.org/G6210502524","display_name":null,"funder_award_id":"307088/2023-5","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"}],"funders":[{"id":"https://openalex.org/F4320321091","display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior","ror":"https://ror.org/00x0ma614"},{"id":"https://openalex.org/F4320322025","display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","ror":"https://ror.org/03swz6y49"},{"id":"https://openalex.org/F4320322749","display_name":"Funda\u00e7\u00e3o Carlos Chagas Filho de Amparo \u00e0 Pesquisa do Estado do Rio de Janeiro","ror":"https://ror.org/03kk0s825"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7221849385.pdf","grobid_xml":"https://content.openalex.org/works/W7221849385.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W1987971958","https://openalex.org/W2038043464","https://openalex.org/W2147152072","https://openalex.org/W2174706414","https://openalex.org/W2180566385","https://openalex.org/W4213009331","https://openalex.org/W4224315235","https://openalex.org/W4235169531","https://openalex.org/W4306377799","https://openalex.org/W4387941534","https://openalex.org/W4391092830","https://openalex.org/W4401043789","https://openalex.org/W4412886804","https://openalex.org/W4414677042","https://openalex.org/W7131811211"],"related_works":["https://openalex.org/W7093718112","https://openalex.org/W4388327657","https://openalex.org/W4411301102","https://openalex.org/W4415710534","https://openalex.org/W7133017175","https://openalex.org/W4412921783","https://openalex.org/W4416042343","https://openalex.org/W4403786514","https://openalex.org/W2964273259","https://openalex.org/W6891937793"],"abstract_inverted_index":{"Topic":[0],"modeling":[1,58],"is":[2],"widely":[3],"used":[4],"to":[5,85],"discover":[6],"and":[7,66,79,105,117,123,134,183],"organize":[8],"latent":[9],"themes":[10],"in":[11,181],"large":[12],"text":[13,103],"collections.":[14],"While":[15],"recent":[16],"embedding-based":[17],"methods":[18,59,73,107],"have":[19,54],"improved":[20],"topic":[21,57,64,87,138,174,186],"discovery":[22],"by":[23],"leveraging":[24],"dense":[25],"semantic":[26],"representations,":[27],"they":[28],"typically":[29],"represent":[30],"topics":[31],"as":[32,52],"lists":[33],"of":[34,61,71,81],"keywords,":[35],"often":[36],"providing":[37,127],"limited":[38],"insights":[39],"into":[40],"the":[41,69,77,82,128,150],"underlying":[42,151],"theme.":[43],"More":[44],"recently,":[45],"Large":[46],"Language":[47],"Model":[48],"(LLM)-based":[49],"approaches,":[50],"such":[51],"TopicGPT,":[53],"introduced":[55],"generative":[56,129],"capable":[60],"producing":[62],"human-readable":[63],"labels":[65],"descriptions.":[67,187],"However,":[68],"effectiveness":[70],"these":[72],"depends":[74],"heavily":[75],"on":[76,161],"quality":[78],"representativeness":[80],"documents":[83,116],"selected":[84],"guide":[86],"generation.":[88],"In":[89],"this":[90],"paper,":[91],"we":[92],"propose":[93],"Core-Periphery":[94],"Sampling":[95],"(CPS),":[96],"a":[97,109],"hybrid":[98],"strategy":[99],"that":[100,120,143],"combines":[101],"classical":[102],"representation":[104,153],"clustering":[106],"with":[108,131],"TopicGPT-inspired":[110],"pipeline.":[111],"CPS":[112,144,164],"selects":[113],"both":[114],"central":[115],"boundary":[118],"instances":[119],"capture":[121],"transitional":[122],"potentially":[124],"informative":[125],"cases,":[126],"model":[130],"an":[132,166],"informed":[133,177],"diverse":[135],"subset":[136],"for":[137,171],"induction.":[139],"Experimental":[140],"results":[141],"show":[142],"outperforms":[145],"random":[146],"sampling,":[147],"particularly":[148],"when":[149],"document":[152,178],"yields":[154],"well-separable":[155],"clusters.":[156],"Although":[157],"BERTopic":[158],"remains":[159],"stronger":[160],"clustering-oriented":[162],"metrics,":[163],"offers":[165],"effective,":[167],"computationally":[168],"simple":[169],"mechanism":[170],"guiding":[172],"LLM-based":[173],"generation":[175],"via":[176],"selection,":[179],"resulting":[180],"coherent":[182],"contextually":[184],"grounded":[185]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-10-16T00:00:00"}