{"id":"https://openalex.org/W2791170418","doi":"https://doi.org/10.1145/3278721.3278729","title":"Measuring and Mitigating Unintended Bias in Text Classification","display_name":"Measuring and Mitigating Unintended Bias in Text Classification","publication_year":2018,"publication_date":"2018-12-27","ids":{"openalex":"https://openalex.org/W2791170418","doi":"https://doi.org/10.1145/3278721.3278729","mag":"2791170418"},"language":"en","primary_location":{"id":"doi:10.1145/3278721.3278729","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3278721.3278729","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3278721.3278729","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3278721.3278729","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103159534","display_name":"Lucas Dixon","orcid":"https://orcid.org/0000-0003-1094-1675"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Lucas Dixon","raw_affiliation_strings":["Google, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Google, New York, NY, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101919661","display_name":"John Li","orcid":"https://orcid.org/0000-0002-3730-3713"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Li","raw_affiliation_strings":["Google, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Google, New York, NY, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110191415","display_name":"Jeffrey Sorensen","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeffrey Sorensen","raw_affiliation_strings":["Google, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Google, New York, NY, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084311372","display_name":"Nithum Thain","orcid":"https://orcid.org/0000-0002-7367-0916"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nithum Thain","raw_affiliation_strings":["Google, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Google, New York, NY, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030217791","display_name":"Lucy Vasserman","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lucy Vasserman","raw_affiliation_strings":["Google, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Google, New York, NY, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5103159534"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":47.5578,"has_fulltext":true,"cited_by_count":665,"citation_normalized_percentile":{"value":0.99840861,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"67","last_page":"73"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9976999759674072,"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":0.9976999759674072,"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":0.9818000197410583,"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/T13629","display_name":"Text Readability and Simplification","score":0.9757000207901001,"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/unintended-consequences","display_name":"Unintended consequences","score":0.8223570585250854},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7756903171539307},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.7120122313499451},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6140701770782471},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5773678421974182},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5391199588775635},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5063544511795044},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.48976659774780273},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.47715944051742554},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3884164094924927},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3777923882007599},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.35869479179382324},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11290574073791504}],"concepts":[{"id":"https://openalex.org/C2776889888","wikidata":"https://www.wikidata.org/wiki/Q1135789","display_name":"Unintended consequences","level":2,"score":0.8223570585250854},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7756903171539307},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.7120122313499451},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6140701770782471},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5773678421974182},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5391199588775635},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5063544511795044},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.48976659774780273},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.47715944051742554},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3884164094924927},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3777923882007599},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35869479179382324},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11290574073791504},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3278721.3278729","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3278721.3278729","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3278721.3278729","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3278721.3278729","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3278721.3278729","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3278721.3278729","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6100000143051147,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2791170418.pdf","grobid_xml":"https://content.openalex.org/works/W2791170418.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W2014352947","https://openalex.org/W2158698691","https://openalex.org/W2511234952","https://openalex.org/W2522104760","https://openalex.org/W2524301210","https://openalex.org/W2540646130","https://openalex.org/W2607719644","https://openalex.org/W2725155646","https://openalex.org/W2728567418","https://openalex.org/W2950018712","https://openalex.org/W2950538796"],"related_works":["https://openalex.org/W2051058708","https://openalex.org/W154868527","https://openalex.org/W1494268238","https://openalex.org/W1983207144","https://openalex.org/W2490706771","https://openalex.org/W2480116122","https://openalex.org/W1976468483","https://openalex.org/W1516574938","https://openalex.org/W2563912921","https://openalex.org/W2407611282"],"abstract_inverted_index":{"We":[0,34,63,85,150],"introduce":[1,139],"and":[2,9,28,50,80,118],"illustrate":[3,35],"a":[4,25,29,46,51,87],"new":[5],"approach":[6,143,154],"to":[7,41,73],"measuring":[8],"mitigating":[10],"unintended":[11,20,74,157],"bias":[12,21,75,124,158],"in":[13,68,76,109],"machine":[14],"learning":[15],"models.":[16],"Our":[17],"definition":[18],"of":[19,31,54,89,97,131],"is":[22,120,140],"parameterized":[23],"by":[24],"test":[26,48],"set":[27,49,88],"subset":[30,96],"input":[32,98],"features.":[33],"how":[36,66],"this":[37,153],"can":[38,71],"be":[39],"used":[40],"evaluate":[42],"text":[43,133],"classifiers":[44],"using":[45],"synthetic":[47],"public":[52],"corpus":[53],"comments":[55],"annotated":[56],"for":[57],"toxicity":[58],"from":[59],"Wikipedia":[60],"Talk":[61],"pages.":[62],"also":[64],"demonstrate":[65,151],"imbalances":[67],"training":[69,148],"data":[70],"lead":[72],"the":[77,95,110,129,132,147,156],"resulting":[78],"models,":[79],"therefore":[81],"potentially":[82],"unfair":[83],"applications.":[84],"use":[86],"common":[90,111],"demographic":[91,114],"identity":[92],"terms":[93],"as":[94],"features":[99],"on":[100,116,128,145],"which":[101],"we":[102,138],"measure":[103],"bias.":[104],"This":[105],"technique":[106],"permits":[107],"analysis":[108],"scenario":[112],"where":[113],"information":[115],"authors":[117],"readers":[119],"unavailable,":[121],"so":[122],"that":[123,152],"mitigation":[125,136],"must":[126],"focus":[127],"content":[130],"itself.":[134],"The":[135],"method":[137],"an":[141],"unsupervised":[142],"based":[144],"balancing":[146],"dataset.":[149],"reduces":[155],"without":[159],"compromising":[160],"overall":[161],"model":[162],"quality.":[163]},"counts_by_year":[{"year":2026,"cited_by_count":16},{"year":2025,"cited_by_count":74},{"year":2024,"cited_by_count":69},{"year":2023,"cited_by_count":108},{"year":2022,"cited_by_count":118},{"year":2021,"cited_by_count":142},{"year":2020,"cited_by_count":82},{"year":2019,"cited_by_count":53},{"year":2018,"cited_by_count":3}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}