{"id":"https://openalex.org/W4409020059","doi":"https://doi.org/10.1109/bigcomp64353.2025.00036","title":"Enhancing Gender Prediction Model Performance through Automatic Individual Entity Extraction and Class Balance","display_name":"Enhancing Gender Prediction Model Performance through Automatic Individual Entity Extraction and Class Balance","publication_year":2025,"publication_date":"2025-02-09","ids":{"openalex":"https://openalex.org/W4409020059","doi":"https://doi.org/10.1109/bigcomp64353.2025.00036"},"language":"en","primary_location":{"id":"doi:10.1109/bigcomp64353.2025.00036","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigcomp64353.2025.00036","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Big Data and Smart Computing (BigComp)","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/A5039698070","display_name":"Chaeyun Kim","orcid":"https://orcid.org/0000-0003-0227-864X"},"institutions":[{"id":"https://openalex.org/I138925566","display_name":"Ewha Womans University","ror":"https://ror.org/053fp5c05","country_code":"KR","type":"education","lineage":["https://openalex.org/I138925566"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Chaeyun Kim","raw_affiliation_strings":["Ewha Womans University,Artificial Intelligence Convergence,Seoul,South Korea"],"affiliations":[{"raw_affiliation_string":"Ewha Womans University,Artificial Intelligence Convergence,Seoul,South Korea","institution_ids":["https://openalex.org/I138925566"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109467915","display_name":"Eunseo Kim","orcid":"https://orcid.org/0000-0001-8450-1520"},"institutions":[{"id":"https://openalex.org/I138925566","display_name":"Ewha Womans University","ror":"https://ror.org/053fp5c05","country_code":"KR","type":"education","lineage":["https://openalex.org/I138925566"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Eunseo Kim","raw_affiliation_strings":["Ewha Womans University,Artificial Intelligence Convergence,Seoul,South Korea"],"affiliations":[{"raw_affiliation_string":"Ewha Womans University,Artificial Intelligence Convergence,Seoul,South Korea","institution_ids":["https://openalex.org/I138925566"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100705002","display_name":"Yeon Hee Kim","orcid":"https://orcid.org/0000-0002-7689-3840"},"institutions":[{"id":"https://openalex.org/I138925566","display_name":"Ewha Womans University","ror":"https://ror.org/053fp5c05","country_code":"KR","type":"education","lineage":["https://openalex.org/I138925566"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yeonhee Kim","raw_affiliation_strings":["Ewha Womans University,Artificial Intelligence Convergence,Seoul,South Korea"],"affiliations":[{"raw_affiliation_string":"Ewha Womans University,Artificial Intelligence Convergence,Seoul,South Korea","institution_ids":["https://openalex.org/I138925566"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013362846","display_name":"Jaehyeong Sim","orcid":"https://orcid.org/0000-0001-8722-8486"},"institutions":[{"id":"https://openalex.org/I138925566","display_name":"Ewha Womans University","ror":"https://ror.org/053fp5c05","country_code":"KR","type":"education","lineage":["https://openalex.org/I138925566"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaehyeong Sim","raw_affiliation_strings":["Ewha Womans University,Department of Computer Science and Engineering,Seoul,South Korea"],"affiliations":[{"raw_affiliation_string":"Ewha Womans University,Department of Computer Science and Engineering,Seoul,South Korea","institution_ids":["https://openalex.org/I138925566"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102911906","display_name":"Jongkil Kim","orcid":"https://orcid.org/0000-0001-5755-108X"},"institutions":[{"id":"https://openalex.org/I138925566","display_name":"Ewha Womans University","ror":"https://ror.org/053fp5c05","country_code":"KR","type":"education","lineage":["https://openalex.org/I138925566"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jongkil Kim","raw_affiliation_strings":["Ewha Womans University,Department of Cyber Security,Seoul,South Korea"],"affiliations":[{"raw_affiliation_string":"Ewha Womans University,Department of Cyber Security,Seoul,South Korea","institution_ids":["https://openalex.org/I138925566"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5039698070"],"corresponding_institution_ids":["https://openalex.org/I138925566"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10316092,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"120","last_page":"121"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.9054999947547913,"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"}},"topics":[{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.9054999947547913,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7012073993682861},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.6074539422988892},{"id":"https://openalex.org/keywords/balance","display_name":"Balance (ability)","score":0.5486007332801819},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4829773008823395},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.48243674635887146},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3307700753211975},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3306906819343567},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.06644994020462036}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7012073993682861},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6074539422988892},{"id":"https://openalex.org/C168031717","wikidata":"https://www.wikidata.org/wiki/Q1530280","display_name":"Balance (ability)","level":2,"score":0.5486007332801819},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4829773008823395},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.48243674635887146},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3307700753211975},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3306906819343567},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.06644994020462036},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigcomp64353.2025.00036","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigcomp64353.2025.00036","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Big Data and Smart Computing (BigComp)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321365","display_name":"Ewha Womans University","ror":"https://ror.org/053fp5c05"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W2020278455","https://openalex.org/W2033059369","https://openalex.org/W4401043472"],"related_works":["https://openalex.org/W2386367800","https://openalex.org/W2353574976","https://openalex.org/W1824021510","https://openalex.org/W2377297411","https://openalex.org/W4384702906","https://openalex.org/W2961085424","https://openalex.org/W3148217948","https://openalex.org/W4224009465","https://openalex.org/W2375788636","https://openalex.org/W2360150702"],"abstract_inverted_index":{"To":[0],"build":[1],"a":[2,13,39,104],"model":[3,78,114],"that":[4,83],"predicts":[5],"the":[6,61,74,84,94,97,111],"gender":[7,98],"of":[8,96,113],"named":[9],"entities":[10,45],"in":[11,73,116],"text,":[12],"high-quality":[14],"labeled":[15],"dataset":[16,75,91],"is":[17],"required,":[18],"which":[19],"requires":[20],"considerable":[21],"manual":[22],"effort":[23],"and":[24,53,65,89,110],"time.":[25],"This":[26,58,101],"paper":[27],"proposes":[28],"two":[29],"major":[30],"contributions":[31],"to":[32,41,76,107],"address":[33],"this":[34],"issue.":[35],"First,":[36],"we":[37,69],"develop":[38],"mechanism":[40],"automatically":[42],"extract":[43],"individual":[44],"from":[46],"sentences":[47],"using":[48],"Named":[49],"Entity":[50],"Recognition":[51],"(NER)":[52],"Part-of-Speech":[54],"(PoS)":[55],"tagging":[56],"techniques.":[57],"approach":[59],"automates":[60],"data":[62,86,108],"generation":[63,87,109],"process":[64],"reduces":[66],"costs.":[67],"Second,":[68],"ensure":[70],"class":[71],"balance":[72],"optimize":[77],"performance.":[79],"Experimental":[80],"results":[81],"demonstrate":[82],"automated":[85],"method":[88],"balanced":[90],"significantly":[92],"enhance":[93],"performance":[95,115],"prediction":[99],"model.":[100],"work":[102],"makes":[103],"substantial":[105],"contribution":[106],"improvement":[112],"Natural":[117],"Language":[118],"Processing":[119],"(NLP)":[120],"tasks.":[121]},"counts_by_year":[],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}