{"id":"https://openalex.org/W4322577842","doi":"https://doi.org/10.1145/3575882.3575905","title":"Performance Comparison of Topic Modeling Algorithms on Indonesian Short Texts","display_name":"Performance Comparison of Topic Modeling Algorithms on Indonesian Short Texts","publication_year":2022,"publication_date":"2022-11-22","ids":{"openalex":"https://openalex.org/W4322577842","doi":"https://doi.org/10.1145/3575882.3575905"},"language":"en","primary_location":{"id":"doi:10.1145/3575882.3575905","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3575882.3575905","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Computer, Control, Informatics and Its Applications","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/A5078524990","display_name":"Nuraisa Novia Hidayati","orcid":"https://orcid.org/0000-0001-5606-8627"},"institutions":[{"id":"https://openalex.org/I4210158665","display_name":"National Nuclear Energy Agency of Indonesia","ror":"https://ror.org/049j1tf72","country_code":"ID","type":"facility","lineage":["https://openalex.org/I4210158665"]},{"id":"https://openalex.org/I4387154144","display_name":"National Research and Innovation Agency","ror":"https://ror.org/02hmjzt55","country_code":"ID","type":"government","lineage":["https://openalex.org/I4387154144"]}],"countries":["ID"],"is_corresponding":true,"raw_author_name":"Nuraisa Novia Hidayati","raw_affiliation_strings":["National Research and Innovation Agency (BRIN), Indonesia"],"raw_orcid":"https://orcid.org/0000-0001-5606-8627","affiliations":[{"raw_affiliation_string":"National Research and Innovation Agency (BRIN), Indonesia","institution_ids":["https://openalex.org/I4210158665","https://openalex.org/I4387154144"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063659856","display_name":"Anne Parlina","orcid":"https://orcid.org/0000-0001-9460-6895"},"institutions":[{"id":"https://openalex.org/I4210158665","display_name":"National Nuclear Energy Agency of Indonesia","ror":"https://ror.org/049j1tf72","country_code":"ID","type":"facility","lineage":["https://openalex.org/I4210158665"]},{"id":"https://openalex.org/I4387154144","display_name":"National Research and Innovation Agency","ror":"https://ror.org/02hmjzt55","country_code":"ID","type":"government","lineage":["https://openalex.org/I4387154144"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Anne Parlina","raw_affiliation_strings":["National Research and Innovation Agency (BRIN), Indonesia"],"raw_orcid":"https://orcid.org/0000-0001-9460-6895","affiliations":[{"raw_affiliation_string":"National Research and Innovation Agency (BRIN), Indonesia","institution_ids":["https://openalex.org/I4210158665","https://openalex.org/I4387154144"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5078524990"],"corresponding_institution_ids":["https://openalex.org/I4210158665","https://openalex.org/I4387154144"],"apc_list":null,"apc_paid":null,"fwci":0.4162,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.69853465,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"117","last_page":"120"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9987000226974487,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9987000226974487,"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/T10028","display_name":"Topic Modeling","score":0.9944000244140625,"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":0.9890999794006348,"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/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.9089202284812927},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7636526823043823},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.7184283137321472},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.6872162818908691},{"id":"https://openalex.org/keywords/gibbs-sampling","display_name":"Gibbs sampling","score":0.6660342812538147},{"id":"https://openalex.org/keywords/indonesian","display_name":"Indonesian","score":0.6528107523918152},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5509341359138489},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4930724799633026},{"id":"https://openalex.org/keywords/dirichlet-distribution","display_name":"Dirichlet distribution","score":0.43596601486206055},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.4256395101547241},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.4205087423324585},{"id":"https://openalex.org/keywords/cover","display_name":"Cover (algebra)","score":0.4158669114112854},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1576681137084961},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.15148481726646423},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14134159684181213},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.11005732417106628}],"concepts":[{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.9089202284812927},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7636526823043823},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.7184283137321472},{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.6872162818908691},{"id":"https://openalex.org/C158424031","wikidata":"https://www.wikidata.org/wiki/Q1191905","display_name":"Gibbs sampling","level":3,"score":0.6660342812538147},{"id":"https://openalex.org/C2779207338","wikidata":"https://www.wikidata.org/wiki/Q9240","display_name":"Indonesian","level":2,"score":0.6528107523918152},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5509341359138489},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4930724799633026},{"id":"https://openalex.org/C169214877","wikidata":"https://www.wikidata.org/wiki/Q981016","display_name":"Dirichlet distribution","level":3,"score":0.43596601486206055},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.4256395101547241},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.4205087423324585},{"id":"https://openalex.org/C2780428219","wikidata":"https://www.wikidata.org/wiki/Q16952335","display_name":"Cover (algebra)","level":2,"score":0.4158669114112854},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1576681137084961},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.15148481726646423},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14134159684181213},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.11005732417106628},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","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/C182310444","wikidata":"https://www.wikidata.org/wiki/Q1332643","display_name":"Boundary value problem","level":2,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","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":1,"locations":[{"id":"doi:10.1145/3575882.3575905","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3575882.3575905","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Computer, Control, Informatics and Its Applications","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1665562618","https://openalex.org/W1902027874","https://openalex.org/W2061922307","https://openalex.org/W2102506741","https://openalex.org/W2511698004","https://openalex.org/W2572380545","https://openalex.org/W2735175355","https://openalex.org/W2887928931","https://openalex.org/W3005792683","https://openalex.org/W3021053579","https://openalex.org/W3043222912","https://openalex.org/W3134842078","https://openalex.org/W3154475157","https://openalex.org/W4245471118","https://openalex.org/W4284960486"],"related_works":["https://openalex.org/W2769501189","https://openalex.org/W4315588616","https://openalex.org/W4312773271","https://openalex.org/W2888805565","https://openalex.org/W2962686197","https://openalex.org/W3005513013","https://openalex.org/W2207653751","https://openalex.org/W2611137333","https://openalex.org/W4389543811","https://openalex.org/W2352674739"],"abstract_inverted_index":{"The":[0,49,83],"number":[1],"of":[2,13,26,31,51,61],"short":[3,27,81],"texts":[4,28],"produced":[5,121],"daily":[6],"has":[7,42],"increased":[8],"significantly":[9],"as":[10],"a":[11],"form":[12],"social":[14],"communication":[15],"commonly":[16],"used":[17],"on":[18,94],"the":[19,32,46,57,62,95,118],"internet.":[20],"Extracting":[21],"topics":[22],"from":[23,79,87],"extensive":[24],"collections":[25],"is":[29,54],"one":[30],"most":[33],"challenging":[34],"tasks":[35],"in":[36,45],"natural":[37],"language":[38],"processing,":[39],"but":[40],"it":[41],"numerous":[43],"applications":[44],"real":[47],"world.":[48],"purpose":[50],"this":[52],"study":[53],"to":[55,128],"compare":[56],"topic":[58,101],"extraction":[59],"performance":[60],"Latent":[63],"Dirichlet":[64,74],"Allocation":[65],"(LDA),":[66],"Non-Negative":[67],"Matrix":[68],"Factorization":[69],"(NMF),":[70],"and":[71,111,124],"Gibbs":[72],"Sampling":[73],"Multinomial":[75],"Mixture":[76],"(GSDMM)":[77],"algorithms":[78],"Indonesian":[80],"texts.":[82],"data":[84],"was":[85],"gathered":[86],"news":[88,97],"articles":[89],"about":[90],"electric":[91],"vehicles":[92],"published":[93],"online":[96],"site":[98],"(Kompas.com).":[99],"Regarding":[100],"coherence":[102],"scores,":[103],"our":[104],"results":[105],"show":[106],"that":[107,117],"LDA":[108],"outperforms":[109],"NMF":[110,123],"GSDMM.":[112],"However,":[113],"human":[114],"judgment":[115],"indicates":[116],"word":[119],"clusters":[120],"by":[122],"GSDMM":[125],"are":[126],"easier":[127],"conclude.":[129]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}