{"id":"https://openalex.org/W3213433026","doi":"https://doi.org/10.1145/3465416.3483291","title":"Breaking Taboos in Fair Machine Learning: An Experimental Study","display_name":"Breaking Taboos in Fair Machine Learning: An Experimental Study","publication_year":2021,"publication_date":"2021-10-05","ids":{"openalex":"https://openalex.org/W3213433026","doi":"https://doi.org/10.1145/3465416.3483291","mag":"3213433026"},"language":"en","primary_location":{"id":"doi:10.1145/3465416.3483291","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3465416.3483291","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Equity and Access in Algorithms, Mechanisms, and Optimization","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/A5017688180","display_name":"Julian Nyarko","orcid":"https://orcid.org/0000-0002-7121-5696"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Julian Nyarko","raw_affiliation_strings":["Stanford University, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027036879","display_name":"Sharad Goel","orcid":"https://orcid.org/0000-0002-6103-9318"},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sharad Goel","raw_affiliation_strings":["Harvard University, USA"],"affiliations":[{"raw_affiliation_string":"Harvard University, USA","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083093359","display_name":"Roseanna Sommers","orcid":"https://orcid.org/0000-0001-8250-6133"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Roseanna Sommers","raw_affiliation_strings":["University of Michigan, USA"],"affiliations":[{"raw_affiliation_string":"University of Michigan, USA","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5017688180"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":3.5759,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.93220581,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"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":0.9993000030517578,"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":0.9993000030517578,"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/T12520","display_name":"Psychology of Moral and Emotional Judgment","score":0.986299991607666,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9549000263214111,"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/computer-science","display_name":"Computer science","score":0.598209023475647},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3722896873950958},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3300839066505432}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.598209023475647},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3722896873950958},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3300839066505432}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3465416.3483291","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3465416.3483291","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Equity and Access in Algorithms, Mechanisms, and Optimization","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.5799999833106995}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W165019788","https://openalex.org/W1487512315","https://openalex.org/W1563119132","https://openalex.org/W1697789815","https://openalex.org/W2157020070","https://openalex.org/W2272449688","https://openalex.org/W2324353751","https://openalex.org/W2478641653","https://openalex.org/W2529369381","https://openalex.org/W2584805976","https://openalex.org/W2617709446","https://openalex.org/W2729790135","https://openalex.org/W2753845591","https://openalex.org/W2773175866","https://openalex.org/W2792934256","https://openalex.org/W2794541067","https://openalex.org/W2885659818","https://openalex.org/W2888456782","https://openalex.org/W2906462581","https://openalex.org/W2908732349","https://openalex.org/W2911495555","https://openalex.org/W2944784741","https://openalex.org/W3014011525","https://openalex.org/W3023523944","https://openalex.org/W3048253689","https://openalex.org/W3060866854","https://openalex.org/W3113471301","https://openalex.org/W3121353240","https://openalex.org/W3121705224","https://openalex.org/W3122385781","https://openalex.org/W3122523118","https://openalex.org/W3123100481","https://openalex.org/W3123374861","https://openalex.org/W3123501078","https://openalex.org/W3124873325","https://openalex.org/W3125130711","https://openalex.org/W3125132731","https://openalex.org/W3125633690","https://openalex.org/W3125934621","https://openalex.org/W3126028293","https://openalex.org/W3126125513","https://openalex.org/W3168162279","https://openalex.org/W3190479309","https://openalex.org/W4205380689","https://openalex.org/W4248633940","https://openalex.org/W6746355153","https://openalex.org/W6805452469"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Many":[0],"scholars,":[1],"engineers,":[2],"and":[3,52,78,112,128,176,202,217,281],"policymakers":[4],"believe":[5],"that":[6,118,137,152,169,192,228],"algorithmic":[7,131,179],"fairness":[8],"requires":[9],"disregarding":[10],"information":[11,63,286],"about":[12,64,189],"certain":[13],"characteristics":[14,276],"of":[15,41,92,126,133,174,255,274,284],"individuals,":[16],"such":[17,285],"as":[18,34,106,108,246,277],"their":[19,233],"race":[20,65,127,175],"or":[21,66],"gender.":[22],"Often,":[23],"the":[24,81,103,124,142,172,190,212,272,282],"mandate":[25],"to":[26,49,72,95,123,141,160,196,249,264],"\u201cblind\u201d":[27],"algorithms":[28,60],"in":[29,56,69,130,158,178,259],"this":[30,86,153],"way":[31,248],"is":[32,47,235,244],"conveyed":[33],"an":[35,239],"unconditional":[36],"ethical":[37],"imperative\u2014a":[38],"minimal":[39],"requirement":[40],"fair":[42],"treatment\u2014and":[43],"any":[44],"contrary":[45],"practice":[46],"assumed":[48],"be":[50],"morally":[51],"politically":[53,289],"untenable.":[54],"However,":[55],"some":[57],"circumstances,":[58],"prohibiting":[59],"from":[61],"considering":[62],"gender":[67,129,177],"can":[68],"fact":[70],"lead":[71,195],"worse":[73],"outcomes":[74,252],"for":[75,83,155,171,200,253],"racial":[76],"minorities":[77],"women,":[79],"complicating":[80],"rationale":[82],"blinding.":[84],"In":[85,165],"paper,":[87],"we":[88,167],"conduct":[89],"a":[90,161,186,247,278],"series":[91],"randomized":[93],"studies":[94],"investigate":[96],"attitudes":[97],"toward":[98],"blinding":[99,156,193,243,262],"algorithms,":[100,232],"both":[101],"among":[102,109,211],"general":[104,213],"public":[105,143],"well":[107],"computer":[110,215],"scientists":[111],"professional":[113,218],"lawyers.":[114,219],"We":[115,149],"find,":[116,150],"first,":[117],"people":[119],"are":[120,209],"generally":[121],"averse":[122],"use":[125,173,283],"determinations":[132],"\u201cpretrial":[134],"risk\u201d\u2014the":[135],"risk":[136],"criminal":[138],"defendants":[139],"pose":[140],"if":[144],"released":[145],"while":[146,224],"awaiting":[147],"trial.":[148],"however,":[151],"preference":[154,234],"shifts":[157],"response":[159],"relatively":[162],"mild":[163],"intervention.":[164],"particular,":[166],"show":[168],"support":[170],"decision-making":[180],"increases":[181],"substantially":[182],"after":[183],"respondents":[184,226,268],"read":[185],"short":[187],"passage":[188],"possibility":[191],"could":[194],"higher":[197],"detention":[198],"rates":[199],"Black":[201],"female":[203],"defendants,":[204],"respectively.":[205],"Similar":[206],"effect":[207],"sizes":[208],"observed":[210],"public,":[214],"scientists,":[216],"These":[220],"findings":[221],"suggest":[222],"that,":[223],"many":[225],"attest":[227],"they":[229],"prefer":[230],"blind":[231],"not":[236],"based":[237],"on":[238],"absolute":[240],"principle.":[241],"Rather,":[242],"perceived":[245],"ensure":[250],"better":[251],"members":[254],"marginalized":[256,266],"groups.":[257],"Accordingly,":[258],"circumstances":[260],"where":[261],"serves":[263],"disadvantage":[265],"groups,":[267],"no":[269],"longer":[270],"view":[271],"exclusion":[273],"protected":[275],"moral":[279],"imperative,":[280],"may":[287],"become":[288],"viable.":[290]},"counts_by_year":[{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}