{"id":"https://openalex.org/W4206709786","doi":"https://doi.org/10.36838/v3i6.5","title":"Reducing Racial and Gender Bias in Machine Learning and Natural Language Processing Tasks Using a GAN Approach","display_name":"Reducing Racial and Gender Bias in Machine Learning and Natural Language Processing Tasks Using a GAN Approach","publication_year":2021,"publication_date":"2021-12-31","ids":{"openalex":"https://openalex.org/W4206709786","doi":"https://doi.org/10.36838/v3i6.5"},"language":"en","primary_location":{"id":"doi:10.36838/v3i6.5","doi":"https://doi.org/10.36838/v3i6.5","is_oa":false,"landing_page_url":"https://doi.org/10.36838/v3i6.5","pdf_url":null,"source":{"id":"https://openalex.org/S4210181049","display_name":"International journal of high school research","issn_l":"2642-1046","issn":["2642-1046","2642-1054"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of High School Research","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"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/A5006718602","display_name":"Isabella S. Mandis","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Isabella S. Mandis","raw_affiliation_strings":["The Spence School, 22 East 91st Street, New York City, NY 10128, USA;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Spence School, 22 East 91st Street, New York City, NY 10128, USA;","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5006718602"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3651,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.60184621,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":95},"biblio":{"volume":"3","issue":"6","first_page":"17","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.9955999851226807,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.9955999851226807,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.0005000000237487257,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.0003000000142492354,"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/algorithmic-bias","display_name":"algorithmic bias","score":0.8889999985694885},{"id":"https://openalex.org/keywords/bias-mitigation","display_name":"bias mitigation","score":0.746999979019165},{"id":"https://openalex.org/keywords/generative-adversarial-networks","display_name":"generative adversarial networks","score":0.996999979019165},{"id":"https://openalex.org/keywords/racial-bias","display_name":"racial bias","score":0.7850000262260437},{"id":"https://openalex.org/keywords/gender-bias","display_name":"gender bias","score":0.9990000128746033},{"id":"https://openalex.org/keywords/income-prediction","display_name":"income prediction","score":0.9739999771118164},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"natural language processing","score":0.6949999928474426},{"id":"https://openalex.org/keywords/hiring-algorithms","display_name":"hiring algorithms","score":0.3580000102519989},{"id":"https://openalex.org/keywords/lending","display_name":"lending","score":0.527999997138977},{"id":"https://openalex.org/keywords/algorithmic-fairness","display_name":"algorithmic fairness","score":0.6800000071525574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5985837578773499},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.5733903050422668},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5092931985855103},{"id":"https://openalex.org/C2983427547","wikidata":"https://www.wikidata.org/wiki/Q93200","display_name":"Gender bias","level":2,"score":0.508995532989502},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4527277946472168},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.38261350989341736},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3634522557258606},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.17283770442008972},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.07796037197113037},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.36838/v3i6.5","doi":"https://doi.org/10.36838/v3i6.5","is_oa":false,"landing_page_url":"https://doi.org/10.36838/v3i6.5","pdf_url":null,"source":{"id":"https://openalex.org/S4210181049","display_name":"International journal of high school research","issn_l":"2642-1046","issn":["2642-1046","2642-1054"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of High School Research","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.9629999995231628,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2725155646","https://openalex.org/W2784397426","https://openalex.org/W2788481061","https://openalex.org/W2899675781","https://openalex.org/W2950018712","https://openalex.org/W2963290659","https://openalex.org/W3108167554","https://openalex.org/W4220820301","https://openalex.org/W4226023486","https://openalex.org/W4298201378"],"related_works":["https://openalex.org/W4392209934","https://openalex.org/W2991302360","https://openalex.org/W3007138654","https://openalex.org/W7166811873","https://openalex.org/W3108989460","https://openalex.org/W2784397426","https://openalex.org/W7206043828","https://openalex.org/W4387079108","https://openalex.org/W2963524349","https://openalex.org/W4385724177"],"abstract_inverted_index":{"While":[0],"organizations":[1],"such":[2,232],"as":[3,233],"Amazon":[4],"have":[5],"used":[6,136,213],"machine":[7,27,47,219],"learning-based":[8],"algorithms":[9,29],"for":[10,183,187,192,196],"their":[11,58,110],"hiring":[12,234],"processes,":[13],"diverse":[14],"employees":[15,235],"are":[16,30,93],"not":[17],"equitably":[18],"hired":[19],"due":[20],"to":[21,25,34,43,57,108,137,166,190,214,229],"biased":[22,75],"datasets.Current":[23],"approaches":[24],"debias":[26,44,138],"learning":[28,48,220],"expensive":[31],"and":[32,60,80,106,112,121,170,185,194],"difficult":[33],"implement.This":[35],"research":[36],"uses":[37,70],"a":[38,45,52,77,95,101,139,145],"Generative":[39],"Adversarial":[40],"Network":[41],"(GAN)":[42],"multi-class":[46,67,168],"classifier's":[49],"prediction":[50],"of":[51,130,181],"person's":[53,102,119],"income":[54],"with":[55],"respect":[56],"race":[59,105,120,184,193],"gender.First,":[61],"it":[62],"is":[63,74,135,159,164],"shown":[64,204],"that":[65,98,116,205],"the":[66,118,124,128,131,133,162,167,171,200,216,223],"classifier,":[68,176],"which":[69,177],"California":[71],"census":[72],"data,":[73],"through":[76],"quantitative":[78],"score":[79],"high":[81],"misclassification":[82],"rates.Next,":[83],"taking":[84],"inspiration":[85],"from":[86,123],"classical":[87],"GAN":[88,134,163],"architecture,":[89],"two":[90],"neural":[91],"networks":[92],"created:":[94],"predictive":[96,125],"network":[97,115],"takes":[99],"in":[100,157,218],"features,":[103],"excluding":[104],"gender,":[107,188],"predict":[109],"income;":[111],"an":[113],"adversarial":[114],"infers":[117],"gender":[122,197],"network.To":[126],"prove":[127],"generalizability":[129],"GAN,":[132],"Natural":[140],"Language":[141],"Processing":[142],"(NLP)":[143],"task:":[144],"word":[146,172],"vector":[147,173],"association":[148,174],"task":[149],"trained":[150],"on":[151],"1,000":[152],"random":[153],"Wikipedia":[154],"articles.A":[155],"decrease":[156,215],"bias":[158,217],"observed":[160],"when":[161],"applied":[165,228],"classifier":[169],"task.The":[175],"originally":[178],"had":[179],"p-%":[180],"39%":[182],"30%":[186],"increased":[189],"76%":[191],"82%":[195],"after":[198],"applying":[199],"GAN.It":[201],"has":[202],"been":[203],"artificial":[206],"intelligence,":[207],"more":[208],"specifically":[209],"GANs,":[210],"can":[211,225],"be":[212,226],"algorithm":[221,224],"outputs;":[222],"easily":[227],"real-world":[230],"situations":[231],"or":[236],"approving":[237],"loans.":[238]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2022-01-26T00:00:00"}