{"id":"https://openalex.org/W4413013003","doi":"https://doi.org/10.1007/s10994-025-06843-9","title":"Assessing the risk of discriminatory bias in classification datasets","display_name":"Assessing the risk of discriminatory bias in classification datasets","publication_year":2025,"publication_date":"2025-08-06","ids":{"openalex":"https://openalex.org/W4413013003","doi":"https://doi.org/10.1007/s10994-025-06843-9"},"language":"en","primary_location":{"id":"doi:10.1007/s10994-025-06843-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-025-06843-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-025-06843-9.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"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":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10994-025-06843-9.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Kejun Dai","orcid":null},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":true,"raw_author_name":"Kejun Dai","raw_affiliation_strings":["Computer Science, University of Auckland, Auckland, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science, University of Auckland, Auckland, New Zealand","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005083044","display_name":"Jonathan Kim","orcid":"https://orcid.org/0000-0002-0289-9035"},"institutions":[{"id":"https://openalex.org/I150510651","display_name":"Callaghan Innovation","ror":"https://ror.org/02n25sf77","country_code":"NZ","type":"government","lineage":["https://openalex.org/I150510651"]},{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Jonathan Kim","raw_affiliation_strings":["AI+, Callaghan Innovation, Auckland, New Zealand","Computer Science, University of Auckland, Auckland, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI+, Callaghan Innovation, Auckland, New Zealand","institution_ids":["https://openalex.org/I150510651"]},{"raw_affiliation_string":"Computer Science, University of Auckland, Auckland, New Zealand","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064609702","display_name":"Sa\u0161o D\u017eeroski","orcid":"https://orcid.org/0000-0003-2363-712X"},"institutions":[{"id":"https://openalex.org/I3006985408","display_name":"Jo\u017eef Stefan Institute","ror":"https://ror.org/05060sz93","country_code":"SI","type":"facility","lineage":["https://openalex.org/I3006985408"]}],"countries":["SI"],"is_corresponding":false,"raw_author_name":"Sa\u0161o D\u017eeroski","raw_affiliation_strings":["Knowledge Technologies, Jo\u017eef Stefan Institute, Ljubljana, Slovenia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Knowledge Technologies, Jo\u017eef Stefan Institute, Ljubljana, Slovenia","institution_ids":["https://openalex.org/I3006985408"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079908211","display_name":"J\u00f6rg Wicker","orcid":"https://orcid.org/0000-0003-0533-3368"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"J\u00f6rg Wicker","raw_affiliation_strings":["Computer Science, University of Auckland, Auckland, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science, University of Auckland, Auckland, New Zealand","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016115576","display_name":"Gillian Dobbie","orcid":"https://orcid.org/0000-0001-7245-0367"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Gillian Dobbie","raw_affiliation_strings":["Computer Science, University of Auckland, Auckland, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science, University of Auckland, Auckland, New Zealand","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055291408","display_name":"Katharina Dost","orcid":"https://orcid.org/0000-0002-1514-0685"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]},{"id":"https://openalex.org/I3006985408","display_name":"Jo\u017eef Stefan Institute","ror":"https://ror.org/05060sz93","country_code":"SI","type":"facility","lineage":["https://openalex.org/I3006985408"]}],"countries":["NZ","SI"],"is_corresponding":true,"raw_author_name":"Katharina Dost","raw_affiliation_strings":["Computer Science, University of Auckland, Auckland, New Zealand","Knowledge Technologies, Jo\u017eef Stefan Institute, Ljubljana, Slovenia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science, University of Auckland, Auckland, New Zealand","institution_ids":["https://openalex.org/I154130895"]},{"raw_affiliation_string":"Knowledge Technologies, Jo\u017eef Stefan Institute, Ljubljana, Slovenia","institution_ids":["https://openalex.org/I3006985408"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5055291408"],"corresponding_institution_ids":["https://openalex.org/I154130895","https://openalex.org/I3006985408"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":{"value":2990,"currency":"USD","value_usd":2990},"fwci":1.2644,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.84982268,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"114","issue":"9","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9861000180244446,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9861000180244446,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.9812999963760376,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9686999917030334,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.5232887864112854},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.48863011598587036},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41666707396507263},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39722758531570435}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5232887864112854},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48863011598587036},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41666707396507263},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39722758531570435}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10994-025-06843-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-025-06843-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-025-06843-9.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"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":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10994-025-06843-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-025-06843-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-025-06843-9.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"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":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2380187409","display_name":null,"funder_award_id":"101081355","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7530123626","display_name":"Knowledge Technologies","funder_award_id":"P2-0103","funder_id":"https://openalex.org/F4320322554","funder_display_name":"Javna Agencija za Raziskovalno Dejavnost RS"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320322554","display_name":"Javna Agencija za Raziskovalno Dejavnost RS","ror":"https://ror.org/059bp8k51"},{"id":"https://openalex.org/F4320334322","display_name":"HORIZON EUROPE Framework Programme","ror":null},{"id":"https://openalex.org/F4320335322","display_name":"European Regional Development Fund","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4413013003.pdf","grobid_xml":"https://content.openalex.org/works/W4413013003.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W1487760768","https://openalex.org/W1565746575","https://openalex.org/W1999954155","https://openalex.org/W2008034251","https://openalex.org/W2014352947","https://openalex.org/W2028138594","https://openalex.org/W2085988980","https://openalex.org/W2118789407","https://openalex.org/W2142334564","https://openalex.org/W2158406371","https://openalex.org/W2200953765","https://openalex.org/W2550925836","https://openalex.org/W2759360483","https://openalex.org/W2893425640","https://openalex.org/W2971238384","https://openalex.org/W2973136425","https://openalex.org/W2974817986","https://openalex.org/W2990138404","https://openalex.org/W3035604179","https://openalex.org/W3126904456","https://openalex.org/W3179553970","https://openalex.org/W3181414820","https://openalex.org/W3202598875","https://openalex.org/W4225409112","https://openalex.org/W4236765470","https://openalex.org/W4289751798","https://openalex.org/W4289766761","https://openalex.org/W4292881157","https://openalex.org/W4310396268","https://openalex.org/W4386954181","https://openalex.org/W4388229648","https://openalex.org/W4392445438","https://openalex.org/W4393119757","https://openalex.org/W4410841480","https://openalex.org/W6680059795","https://openalex.org/W6728551298"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W2033914206"],"abstract_inverted_index":{"Abstract":[0],"Bias":[1],"in":[2,11,50,80,131],"machine":[3],"learning":[4],"models":[5,51],"remains":[6],"a":[7,81,141,175,201],"critical":[8],"challenge,":[9],"particularly":[10],"datasets":[12,99,122],"with":[13],"numeric":[14],"features":[15,42,130],"where":[16],"discrimination":[17,136],"may":[18],"be":[19,63],"subtle":[20],"and":[21,40,89,123],"hard":[22],"to":[23,66,72,90,119,128,133],"detect.":[24],"Existing":[25],"fairness":[26,126],"frameworks":[27,47],"rely":[28,184],"on":[29,185],"expert":[30,186],"knowledge":[31],"of":[32,83,93,143,157,171],"marginalized":[33],"groups,":[34,39],"such":[35,98],"as":[36,168],"specific":[37],"racial":[38],"categorical":[41],"defining":[43],"them.":[44],"Furthermore,":[45],"most":[46],"evaluate":[48],"bias":[49,60,94,158,172],"rather":[52],"than":[53],"datasets,":[54,145],"despite":[55],"the":[56,86,106,191],"fact":[57],"that":[58,152,163,181],"model":[59,101],"can":[61,166],"often":[62],"traced":[64],"back":[65],"dataset":[67,78,87,154],"shortcomings.":[68],"Our":[69,138,160],"research":[70],"aims":[71],"remedy":[73],"this":[74,114],"gap":[75],"by":[76],"capturing":[77],"flaws":[79],"set":[82],"meta-features":[84,151],"at":[85],"level,":[88],"warn":[91],"practitioners":[92],"risk":[95],"when":[96],"using":[97],"for":[100,178,193],"training.":[102],"We":[103],"neither":[104],"restrict":[105],"feature":[107],"type":[108],"nor":[109],"expect":[110],"domain":[111],"knowledge.":[112,187],"To":[113],"end,":[115],"we":[116,148],"develop":[117],"methods":[118],"synthesize":[120],"biased":[121],"extend":[124],"current":[125],"metrics":[127],"continuous":[129],"order":[132],"quantify":[134],"dataset-level":[135,164],"risks.":[137],"approach":[139],"constructs":[140],"meta-database":[142],"diverse":[144],"from":[146],"which":[147],"derive":[149],"transferable":[150],"capture":[153],"properties":[155],"indicative":[156],"risk.":[159],"findings":[161],"demonstrate":[162],"characteristics":[165],"serve":[167],"cost-effective":[169],"indicators":[170],"risk,":[173],"providing":[174],"novel":[176],"method":[177],"data":[179],"auditing":[180],"does":[182],"not":[183],"This":[188],"work":[189],"lays":[190],"foundation":[192],"early-warning":[194],"systems,":[195],"moving":[196],"beyond":[197],"model-focused":[198],"assessments":[199],"toward":[200],"data-centric":[202],"approach.":[203]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}