{"id":"https://openalex.org/W4416799459","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249277","title":"An Information-Theoretic Approach to Data Selection for Generative Topic Modeling","display_name":"An Information-Theoretic Approach to Data Selection for Generative Topic Modeling","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799459","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249277"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249277","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249277","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5093936494","display_name":"Michael Evan Santoso","orcid":"https://orcid.org/0000-0002-5002-0275"},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Michael Evan Santoso","raw_affiliation_strings":["Graduate School of Information Science and Engineering, Ritsumeikan University,Osaka,Japan,5678570"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Engineering, Ritsumeikan University,Osaka,Japan,5678570","institution_ids":["https://openalex.org/I135768898"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120482223","display_name":"Bhone Tay Zar Kyaw","orcid":null},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Bhone Tay Zar Kyaw","raw_affiliation_strings":["Graduate School of Information Science and Engineering, Ritsumeikan University,Osaka,Japan,5678570"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Engineering, Ritsumeikan University,Osaka,Japan,5678570","institution_ids":["https://openalex.org/I135768898"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071033295","display_name":"Valentinus Roby Hananto","orcid":"https://orcid.org/0000-0003-1988-3168"},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Valentinus Roby Hananto","raw_affiliation_strings":["Graduate School of Information Science and Engineering, Ritsumeikan University,Osaka,Japan,5678570"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Engineering, Ritsumeikan University,Osaka,Japan,5678570","institution_ids":["https://openalex.org/I135768898"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046742773","display_name":"Victor V. Kryssanov","orcid":"https://orcid.org/0009-0007-6610-5015"},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Victor Kryssanov","raw_affiliation_strings":["Graduate School of Information Science and Engineering, Ritsumeikan University,Osaka,Japan,5678570"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Engineering, Ritsumeikan University,Osaka,Japan,5678570","institution_ids":["https://openalex.org/I135768898"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17652687,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"694","last_page":"699"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.21230000257492065,"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":0.21230000257492065,"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":0.16429999470710754,"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":0.14010000228881836,"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":0.8781999945640564},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.8228999972343445},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6301000118255615},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6021000146865845},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4797999858856201},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4611999988555908},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.3806000053882599}],"concepts":[{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.8781999945640564},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.8228999972343445},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7760000228881836},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6301000118255615},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6021000146865845},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.554099977016449},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4797999858856201},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4611999988555908},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.44350001215934753},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4036000072956085},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39899998903274536},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3806000053882599},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.37529999017715454},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3711000084877014},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.36739999055862427},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3125},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.29010000824928284},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C141318989","wikidata":"https://www.wikidata.org/wiki/Q5753066","display_name":"Hierarchical Dirichlet process","level":4,"score":0.27619999647140503},{"id":"https://openalex.org/C169214877","wikidata":"https://www.wikidata.org/wiki/Q981016","display_name":"Dirichlet distribution","level":3,"score":0.2662000060081482}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249277","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249277","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2114445178","display_name":null,"funder_award_id":"JPMJSP2101","funder_id":"https://openalex.org/F4320320907","funder_display_name":"Japan Science and Technology Corporation"}],"funders":[{"id":"https://openalex.org/F4320320907","display_name":"Japan Science and Technology Corporation","ror":"https://ror.org/00097mb19"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1602214198","https://openalex.org/W1612700042","https://openalex.org/W1969195332","https://openalex.org/W1995637454","https://openalex.org/W2032558547","https://openalex.org/W2038043464","https://openalex.org/W2093585809","https://openalex.org/W2146341620","https://openalex.org/W2150731624","https://openalex.org/W2742034229","https://openalex.org/W2972419743","https://openalex.org/W3139257635","https://openalex.org/W3200230513","https://openalex.org/W4206729245","https://openalex.org/W4229011615","https://openalex.org/W4231510805","https://openalex.org/W4241760637","https://openalex.org/W4250619709","https://openalex.org/W4306377799","https://openalex.org/W4395081685","https://openalex.org/W4410112344"],"related_works":[],"abstract_inverted_index":{"Topic":[0],"modeling":[1],"is":[2,15,41],"widely":[3],"used":[4],"to":[5,22],"extract":[6],"meaningful":[7],"themes":[8],"from":[9,119],"large":[10],"text":[11],"corpora.":[12],"Typically,":[13],"it":[14],"assumed":[16],"that":[17,28,51,92,113],"all":[18],"documents":[19,118],"contribute":[20],"equally":[21],"topic":[23,34,56,66,81,105,127],"extraction,":[24],"ignoring":[25],"the":[26,33,48,54,62,86,103,120,126,133],"fact":[27],"corpus":[29],"composition":[30],"directly":[31],"determines":[32],"model":[35,57,67,106],"performance.":[36,58],"The":[37,129],"entire":[38],"document":[39,49],"dataset":[40],"then":[42],"processed":[43],"without":[44],"considering":[45],"variations":[46],"in":[47,69,124],"quality":[50],"can":[52],"affect":[53],"generated":[55],"This":[59],"paper":[60,130],"introduces":[61],"concept":[63],"of":[64,71],"a":[65,76],"well-formed":[68,104],"terms":[70],"information":[72],"theory,":[73],"and":[74,88,136],"proposes":[75],"data":[77,100],"selection":[78],"algorithm":[79],"for":[80,139],"modeling.":[82],"Experimental":[83],"results":[84,111,123],"on":[85,99],"Reuters":[87],"Wikipedia":[89],"corpora":[90],"demonstrated":[91],"Latent":[93],"Dirichlet":[94],"Allocation":[95],"(LDA)":[96],"models":[97],"trained":[98],"selected":[101],"using":[102],"outperform":[107],"baseline":[108],"models.":[109],"These":[110],"confirmed":[112],"removing":[114],"noisy":[115],"or":[116],"unrepresentative":[117],"generative":[121],"process":[122],"improving":[125],"quality.":[128],"briefly":[131],"discusses":[132],"main":[134],"findings":[135],"highlights":[137],"directions":[138],"future":[140],"study.":[141]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-28T00:00:00"}