{"id":"https://openalex.org/W4407304448","doi":"https://doi.org/10.1109/access.2025.3540410","title":"Automatic Seed Word Selection for Topic Modeling","display_name":"Automatic Seed Word Selection for Topic Modeling","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4407304448","doi":"https://doi.org/10.1109/access.2025.3540410"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3540410","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3540410","pdf_url":null,"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://doi.org/10.1109/access.2025.3540410","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5096831182","display_name":"Dahyun Jeong","orcid":null},"institutions":[{"id":"https://openalex.org/I124633538","display_name":"University of Seoul","ror":"https://ror.org/05en5nh73","country_code":"KR","type":"education","lineage":["https://openalex.org/I124633538"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dahyun Jeong","raw_affiliation_strings":["Department of Statistics, University of Seoul, Seoul, South Korea","Department of Statistics, University of Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics, University of Seoul, Seoul, South Korea","institution_ids":["https://openalex.org/I124633538"]},{"raw_affiliation_string":"Department of Statistics, University of Seoul, South Korea","institution_ids":["https://openalex.org/I124633538"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101025244","display_name":"Jeong-in Hwang","orcid":null},"institutions":[{"id":"https://openalex.org/I124633538","display_name":"University of Seoul","ror":"https://ror.org/05en5nh73","country_code":"KR","type":"education","lineage":["https://openalex.org/I124633538"]},{"id":"https://openalex.org/I1317225278","display_name":"Statistics Korea","ror":"https://ror.org/004g7jm05","country_code":"KR","type":"government","lineage":["https://openalex.org/I1317225278","https://openalex.org/I2801339556","https://openalex.org/I4210126005"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jeongin Hwang","raw_affiliation_strings":["Department of Statistical Data Science, University of Seoul, Seoul, South Korea","Department of Statistical Data Science, University of Seoul, South Korea"],"raw_orcid":"https://orcid.org/0009-0004-4545-568X","affiliations":[{"raw_affiliation_string":"Department of Statistical Data Science, University of Seoul, Seoul, South Korea","institution_ids":["https://openalex.org/I1317225278"]},{"raw_affiliation_string":"Department of Statistical Data Science, University of Seoul, South Korea","institution_ids":["https://openalex.org/I124633538"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110996221","display_name":"Yunjin Choi","orcid":null},"institutions":[{"id":"https://openalex.org/I124633538","display_name":"University of Seoul","ror":"https://ror.org/05en5nh73","country_code":"KR","type":"education","lineage":["https://openalex.org/I124633538"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yunjin Choi","raw_affiliation_strings":["Department of Statistics, University of Seoul, Seoul, South Korea","Department of Statistics, University of Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-0194-5802","affiliations":[{"raw_affiliation_string":"Department of Statistics, University of Seoul, Seoul, South Korea","institution_ids":["https://openalex.org/I124633538"]},{"raw_affiliation_string":"Department of Statistics, University of Seoul, South Korea","institution_ids":["https://openalex.org/I124633538"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044632351","display_name":"Yoon-Yeong Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I124633538","display_name":"University of Seoul","ror":"https://ror.org/05en5nh73","country_code":"KR","type":"education","lineage":["https://openalex.org/I124633538"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yoon-Yeong Kim","raw_affiliation_strings":["Department of Statistics, University of Seoul, Seoul, South Korea","Department of Statistics, University of Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0003-3696-6571","affiliations":[{"raw_affiliation_string":"Department of Statistics, University of Seoul, Seoul, South Korea","institution_ids":["https://openalex.org/I124633538"]},{"raw_affiliation_string":"Department of Statistics, University of Seoul, South Korea","institution_ids":["https://openalex.org/I124633538"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00885665,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":null,"first_page":"31269","last_page":"31285"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9660000205039978,"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":0.9660000205039978,"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":0.9401000142097473,"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/T13274","display_name":"Expert finding and Q&A systems","score":0.9150999784469604,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.7493719458580017},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6948887705802917},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5944958329200745},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5365199446678162},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5013339519500732},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1261802613735199}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7493719458580017},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6948887705802917},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5944958329200745},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5365199446678162},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5013339519500732},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1261802613735199},{"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.2025.3540410","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3540410","pdf_url":null,"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:790437a990324eb285be562be77e7d5c","is_oa":true,"landing_page_url":"https://doaj.org/article/790437a990324eb285be562be77e7d5c","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 13, Pp 31269-31285 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3540410","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3540410","pdf_url":null,"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":[],"awards":[{"id":"https://openalex.org/G3784053640","display_name":null,"funder_award_id":"2022R1A4A3033874","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W746911252","https://openalex.org/W1493526108","https://openalex.org/W1973036367","https://openalex.org/W1992862710","https://openalex.org/W2048330531","https://openalex.org/W2074909580","https://openalex.org/W2096110600","https://openalex.org/W2150593711","https://openalex.org/W2151703435","https://openalex.org/W2158085718","https://openalex.org/W2165664073","https://openalex.org/W2179548002","https://openalex.org/W2250275424","https://openalex.org/W2250533720","https://openalex.org/W2252027530","https://openalex.org/W2533513334","https://openalex.org/W2744190418","https://openalex.org/W2759170062","https://openalex.org/W2787894218","https://openalex.org/W2889326414","https://openalex.org/W2893640826","https://openalex.org/W2904614016","https://openalex.org/W2914138217","https://openalex.org/W2963766892","https://openalex.org/W3004011066","https://openalex.org/W3004119480","https://openalex.org/W3007329240","https://openalex.org/W3015674157","https://openalex.org/W3045464143","https://openalex.org/W4200428021","https://openalex.org/W4220861476","https://openalex.org/W4226267509","https://openalex.org/W4229009238","https://openalex.org/W4235169531","https://openalex.org/W4321480042","https://openalex.org/W4362454468","https://openalex.org/W4367555978","https://openalex.org/W4378672704","https://openalex.org/W4385571952","https://openalex.org/W4398161448","https://openalex.org/W4401043789","https://openalex.org/W4402950130","https://openalex.org/W6628750762","https://openalex.org/W6630417432","https://openalex.org/W6633359351","https://openalex.org/W6639619044","https://openalex.org/W6674222484","https://openalex.org/W6683333316","https://openalex.org/W6751854905","https://openalex.org/W6755207826","https://openalex.org/W6810311456","https://openalex.org/W6843398536"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W3204019825","https://openalex.org/W2296205523"],"abstract_inverted_index":{"Topic":[0],"modeling":[1,55],"is":[2,190],"widely":[3],"used":[4],"to":[5,18,23,26,87,150,226],"uncover":[6],"latent":[7],"semantic":[8],"topics":[9,21],"from":[10],"a":[11,98,167],"corpus.":[12],"However,":[13],"topic":[14,50,54,199,211],"models":[15],"often":[16],"struggle":[17],"identify":[19],"minor":[20],"due":[22],"their":[24],"tendency":[25],"prioritize":[27],"dominant":[28],"patterns":[29],"in":[30,46,105,166],"the":[31,100],"data.":[32,96],"They":[33],"are":[34,81],"also":[35],"hindered":[36],"by":[37,59,83],"polysemous":[38],"words":[39,104],"and":[40,85,125,189,204,210],"general":[41],"terms,":[42],"which":[43],"frequently":[44],"appear":[45],"multiple":[47,208],"contexts,":[48],"making":[49],"assignment":[51],"difficult.":[52],"Seed-guided":[53],"addresses":[56],"these":[57,112],"issues":[58],"incorporating":[60],"prior":[61,156],"knowledge":[62],"through":[63,229],"\u201cseed":[64],"words\u201d.":[65],"Existing":[66],"approaches,":[67],"however,":[68],"primarily":[69],"rely":[70],"on":[71,130],"supervised":[72,230],"selection":[73,101,120],"using":[74],"label-dependent":[75],"metrics":[76],"or":[77,175],"manual":[78],"selection.":[79,233],"Both":[80],"limited":[82],"scalability":[84],"susceptible":[86],"human":[88,176],"bias,":[89],"particularly":[90],"when":[91],"dealing":[92],"with":[93,137],"unstructured":[94],"real-world":[95],"As":[97],"result,":[99],"of":[102],"seed":[103,118,231],"unsupervised":[106,169],"settings":[107],"remains":[108],"underexplored.":[109],"To":[110],"address":[111],"challenges,":[113],"we":[114,213],"propose":[115],"an":[116,145],"automated":[117],"word":[119,127,153,232],"process":[121,136],"that":[122,147,215],"identifies":[123],"diverse":[124],"cohesive":[126],"sets":[128],"based":[129],"inter-word":[131],"relationships.":[132],"We":[133],"instantiate":[134],"this":[135],"<inline-formula":[138,158,178,216],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[139,159,179,217],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">":[140,160,180,218],"<tex-math":[141,161,181,219],"notation=\"LaTeX\">$\\textsf":[142,162,182,220],"{SeedCapture}$":[143,163,183,221],"</tex-math></inline-formula>,":[144],"algorithm":[146],"utilizes":[148],"co-occurrence":[149],"capture":[151],"meaningful":[152],"associations.":[154],"Unlike":[155],"methods,":[157],"</tex-math></inline-formula>":[164,184,222],"operates":[165],"fully":[168],"manner,":[170],"requiring":[171],"no":[172],"predefined":[173],"labels":[174],"intervention.":[177],"requires":[185],"minimal":[186],"parameter":[187],"tuning":[188],"highly":[191],"adaptable,":[192],"enabling":[193],"seamless":[194],"integration":[195],"into":[196],"existing":[197],"seed-guided":[198],"models.":[200],"Through":[201],"extensive":[202],"quantitative":[203],"qualitative":[205],"evaluations":[206],"across":[207],"datasets":[209],"models,":[212],"demonstrate":[214],"achieves":[223],"results":[224],"comparable":[225],"those":[227],"obtained":[228]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}