{"id":"https://openalex.org/W4321504623","doi":"https://doi.org/10.1007/978-3-031-26438-2_18","title":"Identity Term Sampling for\u00a0Measuring Gender Bias in\u00a0Training Data","display_name":"Identity Term Sampling for\u00a0Measuring Gender Bias in\u00a0Training Data","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4321504623","doi":"https://doi.org/10.1007/978-3-031-26438-2_18"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-26438-2_18","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-031-26438-2_18","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-031-26438-2_18.pdf","source":{"id":"https://openalex.org/S2764900261","display_name":"Communications in computer and information science","issn_l":"1865-0929","issn":["1865-0929","1865-0937"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Communications in Computer and Information Science","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/978-3-031-26438-2_18.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086728188","display_name":"Nasim Sobhani","orcid":null},"institutions":[{"id":"https://openalex.org/I4210144925","display_name":"Technological University Dublin","ror":"https://ror.org/04t0qbt32","country_code":"IE","type":"education","lineage":["https://openalex.org/I4210144925"]}],"countries":["IE"],"is_corresponding":true,"raw_author_name":"Nasim Sobhani","raw_affiliation_strings":["Technological University Dublin, Dublin, Ireland"],"affiliations":[{"raw_affiliation_string":"Technological University Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I4210144925"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067047073","display_name":"Sarah Jane Delany","orcid":"https://orcid.org/0000-0002-2062-7439"},"institutions":[{"id":"https://openalex.org/I4210144925","display_name":"Technological University Dublin","ror":"https://ror.org/04t0qbt32","country_code":"IE","type":"education","lineage":["https://openalex.org/I4210144925"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Sarah Jane Delany","raw_affiliation_strings":["Technological University Dublin, Dublin, Ireland"],"affiliations":[{"raw_affiliation_string":"Technological University Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I4210144925"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5086728188"],"corresponding_institution_ids":["https://openalex.org/I4210144925"],"apc_list":null,"apc_paid":null,"fwci":1.0624,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.7436515,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"226","last_page":"238"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9994999766349792,"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/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9994999766349792,"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":0.9947999715805054,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9898999929428101,"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/gender-bias","display_name":"Gender bias","score":0.7444647550582886},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.687079668045044},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6819164752960205},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.5452360510826111},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5305030345916748},{"id":"https://openalex.org/keywords/gender-identity","display_name":"Gender identity","score":0.5104326605796814},{"id":"https://openalex.org/keywords/sampling-bias","display_name":"Sampling bias","score":0.4994792938232422},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.48642659187316895},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4834955036640167},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46462589502334595},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3287147879600525},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.28690680861473083},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.18095403909683228},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.13630229234695435},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08131548762321472},{"id":"https://openalex.org/keywords/sample-size-determination","display_name":"Sample size determination","score":0.06962761282920837}],"concepts":[{"id":"https://openalex.org/C2983427547","wikidata":"https://www.wikidata.org/wiki/Q93200","display_name":"Gender bias","level":2,"score":0.7444647550582886},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.687079668045044},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6819164752960205},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.5452360510826111},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5305030345916748},{"id":"https://openalex.org/C2991839931","wikidata":"https://www.wikidata.org/wiki/Q48264","display_name":"Gender identity","level":2,"score":0.5104326605796814},{"id":"https://openalex.org/C75917345","wikidata":"https://www.wikidata.org/wiki/Q2725298","display_name":"Sampling bias","level":3,"score":0.4994792938232422},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.48642659187316895},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4834955036640167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46462589502334595},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3287147879600525},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.28690680861473083},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.18095403909683228},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.13630229234695435},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08131548762321472},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.06962761282920837},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/978-3-031-26438-2_18","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-031-26438-2_18","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-031-26438-2_18.pdf","source":{"id":"https://openalex.org/S2764900261","display_name":"Communications in computer and information science","issn_l":"1865-0929","issn":["1865-0929","1865-0937"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Communications in Computer and Information Science","raw_type":"book-chapter"},{"id":"pmh:oai:arrow.tudublin.ie:ansscon-1001","is_oa":true,"landing_page_url":"https://arrow.tudublin.ie/ansscon/1","pdf_url":null,"source":{"id":"https://openalex.org/S4377196307","display_name":"Arrow - TU Dublin (Technological University Dublin)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210144925","host_organization_name":"Technological University Dublin","host_organization_lineage":["https://openalex.org/I4210144925"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Conference Papers","raw_type":"conferencepaper"},{"id":"doi:10.21427/bkm6-rf06","is_oa":true,"landing_page_url":"https://doi.org/10.21427/bkm6-rf06","pdf_url":null,"source":{"id":"https://openalex.org/S4306402084","display_name":"ARROW@Dublin Institute of Technology (Dublin Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I115570527","host_organization_name":"Dublin Institute of Technology","host_organization_lineage":["https://openalex.org/I115570527"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.1007/978-3-031-26438-2_18","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-031-26438-2_18","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-031-26438-2_18.pdf","source":{"id":"https://openalex.org/S2764900261","display_name":"Communications in computer and information science","issn_l":"1865-0929","issn":["1865-0929","1865-0937"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Communications in Computer and Information Science","raw_type":"book-chapter"},"sustainable_development_goals":[{"score":0.5400000214576721,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320847","display_name":"Science Foundation Ireland","ror":"https://ror.org/0271asj38"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4321504623.pdf"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W2473555522","https://openalex.org/W2483215953","https://openalex.org/W2739810148","https://openalex.org/W2785615365","https://openalex.org/W2791170418","https://openalex.org/W2802105481","https://openalex.org/W2893425640","https://openalex.org/W2899501643","https://openalex.org/W2909212904","https://openalex.org/W2926555354","https://openalex.org/W2950888501","https://openalex.org/W2962739339","https://openalex.org/W2962787423","https://openalex.org/W2962990575","https://openalex.org/W2963526187","https://openalex.org/W2972663293","https://openalex.org/W2972668795","https://openalex.org/W2972735048","https://openalex.org/W3105882417","https://openalex.org/W3176477796","https://openalex.org/W4385574250","https://openalex.org/W6835584955"],"related_works":["https://openalex.org/W4280521274","https://openalex.org/W2299309501","https://openalex.org/W2072676583","https://openalex.org/W2052665155","https://openalex.org/W1997937452","https://openalex.org/W2970859251","https://openalex.org/W2918060409","https://openalex.org/W3193874062","https://openalex.org/W3177318739","https://openalex.org/W4321504623"],"abstract_inverted_index":{"Abstract":[0],"Predictions":[1],"from":[2,116],"machine":[3],"learning":[4],"models":[5],"can":[6,191],"reflect":[7],"biases":[8],"in":[9,22,41,81,102,135,164],"the":[10,51,56,60,117,121,129,147],"data":[11,43,105,196],"on":[12,55,194],"which":[13,145,153],"they":[14],"are":[15,157],"trained.":[16],"Gender":[17,140],"bias":[18,40,101,163,181],"has":[19,198],"been":[20],"identified":[21,115],"natural":[23],"language":[24],"processing":[25],"systems":[26,109],"such":[27],"as":[28,139,184,186],"those":[29],"used":[30,158,193],"for":[31,73,83,106,161],"recruitment.":[32],"The":[33,124],"development":[34],"of":[35,53,62,76,120,149,178],"approaches":[36],"to":[37,46,49,58,68,99,159],"mitigate":[38],"gender":[39,54,72,91,113,155,162,180,201],"training":[42,77,104,122,195],"typically":[44],"need":[45],"be":[47,192],"able":[48],"isolate":[50,69,154],"effect":[52],"output":[57],"see":[59],"impact":[61],"gender.":[63],"While":[64],"it":[65],"is":[66,88,126,176],"possible":[67],"and":[70,156,190],"identify":[71],"some":[74],"types":[75],"data,":[78],"e.g.":[79],"CVs":[80],"recruitment,":[82],"most":[84],"textual":[85,103,118],"corpora":[86],"there":[87],"no":[89,199],"obvious":[90,200],"label.":[92,202],"This":[93],"paper":[94],"proposes":[95],"a":[96,112,165],"general":[97],"approach":[98,125,133,175],"measure":[100],"NLP":[107],"prediction":[108],"by":[110],"providing":[111],"label":[114],"content":[119],"data.":[123],"compared":[127],"with":[128],"identity":[130,187],"term":[131,188],"template":[132],"currently":[134],"use,":[136],"also":[137],"known":[138],"Bias":[141],"Evaluation":[142],"Datasets":[143],"(GBETs),":[144],"involves":[146],"design":[148],"synthetic":[150],"test":[151],"datasets":[152],"probe":[160],"dataset.":[166],"We":[167],"show":[168],"that":[169,197],"our":[170],"Identity":[171],"Term":[172],"Sampling":[173],"(ITS)":[174],"capable":[177],"identifying":[179],"at":[182],"least":[183],"well":[185],"templates":[189]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}