{"id":"https://openalex.org/W4280548710","doi":"https://doi.org/10.1145/3531146.3533105","title":"De-biasing \u201cbias\u201d measurement","display_name":"De-biasing \u201cbias\u201d measurement","publication_year":2022,"publication_date":"2022-06-20","ids":{"openalex":"https://openalex.org/W4280548710","doi":"https://doi.org/10.1145/3531146.3533105"},"language":"en","primary_location":{"id":"doi:10.1145/3531146.3533105","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3531146.3533105","pdf_url":null,"source":{"id":"https://openalex.org/S4363608463","display_name":"2022 ACM Conference on Fairness, Accountability, and Transparency","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 ACM Conference on Fairness Accountability and Transparency","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2205.05770","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034482692","display_name":"Kristian Lum","orcid":"https://orcid.org/0000-0003-2637-5612"},"institutions":[{"id":"https://openalex.org/I113979032","display_name":"Twitter (United States)","ror":"https://ror.org/04wt43v05","country_code":"US","type":"company","lineage":["https://openalex.org/I113979032"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kristian Lum","raw_affiliation_strings":["Twitter, USA"],"affiliations":[{"raw_affiliation_string":"Twitter, USA","institution_ids":["https://openalex.org/I113979032"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043987765","display_name":"Yunfeng Zhang","orcid":"https://orcid.org/0000-0003-2418-2120"},"institutions":[{"id":"https://openalex.org/I113979032","display_name":"Twitter (United States)","ror":"https://ror.org/04wt43v05","country_code":"US","type":"company","lineage":["https://openalex.org/I113979032"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yunfeng Zhang","raw_affiliation_strings":["Twitter, USA"],"affiliations":[{"raw_affiliation_string":"Twitter, USA","institution_ids":["https://openalex.org/I113979032"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036699573","display_name":"Amanda Bower","orcid":"https://orcid.org/0000-0002-4497-3088"},"institutions":[{"id":"https://openalex.org/I113979032","display_name":"Twitter (United States)","ror":"https://ror.org/04wt43v05","country_code":"US","type":"company","lineage":["https://openalex.org/I113979032"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amanda Bower","raw_affiliation_strings":["Twitter, USA"],"affiliations":[{"raw_affiliation_string":"Twitter, USA","institution_ids":["https://openalex.org/I113979032"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5034482692"],"corresponding_institution_ids":["https://openalex.org/I113979032"],"apc_list":null,"apc_paid":null,"fwci":2.6552,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.90467626,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"379","last_page":"389"},"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":0.9948999881744385,"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"}},"topics":[{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.9948999881744385,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/biasing","display_name":"Biasing","score":0.8120099306106567},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.41855093836784363},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.16903287172317505},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.1596982777118683},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1138228178024292}],"concepts":[{"id":"https://openalex.org/C20254490","wikidata":"https://www.wikidata.org/wiki/Q719550","display_name":"Biasing","level":3,"score":0.8120099306106567},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.41855093836784363},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.16903287172317505},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.1596982777118683},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1138228178024292}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3531146.3533105","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3531146.3533105","pdf_url":null,"source":{"id":"https://openalex.org/S4363608463","display_name":"2022 ACM Conference on Fairness, Accountability, and Transparency","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 ACM Conference on Fairness Accountability and Transparency","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2205.05770","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2205.05770","pdf_url":"https://arxiv.org/pdf/2205.05770","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2205.05770","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2205.05770","pdf_url":"https://arxiv.org/pdf/2205.05770","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.49000000953674316,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1982585616","https://openalex.org/W1995945562","https://openalex.org/W1999649023","https://openalex.org/W2100960835","https://openalex.org/W2154449833","https://openalex.org/W2315123323","https://openalex.org/W2704480242","https://openalex.org/W2888421747","https://openalex.org/W2898851569","https://openalex.org/W2950173087","https://openalex.org/W2963106283","https://openalex.org/W2963116854","https://openalex.org/W2963917042","https://openalex.org/W2964116855","https://openalex.org/W2969670093","https://openalex.org/W3006437051","https://openalex.org/W3031923829","https://openalex.org/W3048991518","https://openalex.org/W3081286828","https://openalex.org/W3102092462","https://openalex.org/W3103891807","https://openalex.org/W3106489865","https://openalex.org/W3157826390","https://openalex.org/W3203944849","https://openalex.org/W4289751798","https://openalex.org/W4290840946"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2069427488","https://openalex.org/W4281694563","https://openalex.org/W2080696413","https://openalex.org/W2163182355","https://openalex.org/W1506140395","https://openalex.org/W4232799642","https://openalex.org/W2912082923","https://openalex.org/W2744827311"],"abstract_inverted_index":{"When":[0],"a":[1,209],"model\u2019s":[2],"performance":[3,51,79,116,144,180,221,228,244],"differs":[4],"across":[5,181],"socially":[6],"or":[7,13,194],"culturally":[8],"relevant":[9],"groups\u2013like":[10],"race,":[11],"gender,":[12],"the":[14,27,33,109,124,140,164,176,199,236,238],"intersections":[15],"of":[16,26,43,48,77,108,123,157,175,178,201,217],"many":[17,107],"such":[18,55],"groups\u2013it":[19],"is":[20,184],"often":[21],"called":[22],"\u201dbiased.\u201d":[23],"While":[24],"much":[25,57],"work":[28,59],"in":[29,150,235,242],"algorithmic":[30],"fairness":[31,45],"over":[32],"last":[34],"several":[35],"years":[36],"has":[37,60],"focused":[38],"on":[39,208],"developing":[40],"various":[41],"definitions":[42],"model":[44,50,78,115,143,179,218,220,227,243],"(the":[46],"absence":[47],"group-wise":[49,114,142,219,240],"disparities)":[52],"and":[53,81,103,172,187,206],"eliminating":[54],"\u201cbias,\u201d":[56],"less":[58],"gone":[61],"into":[62,92],"rigorously":[63],"measuring":[64],"it.":[65],"In":[66,96],"practice,":[67],"it":[68],"important":[69],"to":[70,112,129],"have":[71],"high":[72],"quality,":[73],"human":[74],"digestible":[75],"measures":[76],"disparities":[80,117,145,222,241],"associated":[82],"uncertainty":[83,173],"quantification":[84,174],"about":[85,139],"them":[86],"that":[87,106,133,212],"can":[88,135],"serve":[89],"as":[90],"inputs":[91],"multi-faceted":[93],"decision-making":[94],"processes.":[95],"this":[97,134,202],"paper,":[98],"we":[99],"show":[100,207],"both":[101],"mathematically":[102],"through":[104,204],"simulation":[105,205],"metrics":[110],"used":[111],"measure":[113],"are":[118,245],"themselves":[119],"statistically":[120,214,224,248],"biased":[121,215],"estimators":[122,216],"underlying":[125],"quantities":[126],"they":[127],"purport":[128],"represent.":[130],"We":[131,162,197],"argue":[132],"cause":[136],"misleading":[137],"conclusions":[138],"relative":[141],"along":[146],"different":[147],"dimensions,":[148],"especially":[149],"cases":[151],"where":[152],"some":[153],"sensitive":[154],"variables":[155],"consist":[156],"categories":[158],"with":[159],"few":[160],"members.":[161],"propose":[163],"\u201cdouble-corrected\u201d":[165],"variance":[166,177],"estimator,":[167,237],"which":[168],"provides":[169],"unbiased":[170],"estimates":[171],"groups.":[182],"It":[183],"conceptually":[185],"simple":[186],"easily":[188],"implementable":[189],"without":[190],"statistical":[191,233],"software":[192],"package":[193],"numerical":[195],"optimization.":[196],"demonstrate":[198],"utility":[200],"approach":[203],"real":[210],"dataset":[211],"while":[213],"indicate":[223],"significant":[225],"between-group":[226],"disparities,":[229],"when":[230],"accounting":[231],"for":[232],"bias":[234],"estimated":[239],"no":[246],"longer":[247],"significant.":[249]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":4}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}