{"id":"https://openalex.org/W3030633889","doi":"https://doi.org/10.1145/3334480.3382949","title":"A General Methodology to Quantify Biases in Natural Language Data","display_name":"A General Methodology to Quantify Biases in Natural Language Data","publication_year":2020,"publication_date":"2020-04-25","ids":{"openalex":"https://openalex.org/W3030633889","doi":"https://doi.org/10.1145/3334480.3382949","mag":"3030633889"},"language":"en","primary_location":{"id":"doi:10.1145/3334480.3382949","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3334480.3382949","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Extended Abstracts of the 2020 CHI Conference on Human Factors in Computing Systems","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/A5100362824","display_name":"Jiawei Chen","orcid":"https://orcid.org/0000-0002-9759-9747"},"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":"Jiawei Chen","raw_affiliation_strings":["Google, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053418697","display_name":"Anbang Xu","orcid":"https://orcid.org/0009-0005-9707-7817"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anbang Xu","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068582966","display_name":"Zhe Liu","orcid":"https://orcid.org/0000-0002-8300-1855"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhe Liu","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018249303","display_name":"Yufan Guo","orcid":"https://orcid.org/0000-0001-6137-010X"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yufan Guo","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100340834","display_name":"Xiaotong Liu","orcid":"https://orcid.org/0000-0002-3618-0168"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaotong Liu","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069272424","display_name":"Yingbei Tong","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yingbei Tong","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065701116","display_name":"Rama Akkiraju","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rama Akkiraju","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054610664","display_name":"John M. Carroll","orcid":"https://orcid.org/0000-0001-5189-337X"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John M. Carroll","raw_affiliation_strings":["Pennsylvania State University, University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5100362824"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":0.3977,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.67738761,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9861999750137329,"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":0.9861999750137329,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.9821000099182129,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"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/T10028","display_name":"Topic Modeling","score":0.9466000199317932,"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":0.785993218421936},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.7707712650299072},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5989698171615601},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5949351191520691},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5493199825286865},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.525063693523407},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4629533886909485},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.42882055044174194},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.42673659324645996},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3202856481075287}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.785993218421936},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.7707712650299072},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5989698171615601},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5949351191520691},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5493199825286865},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.525063693523407},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4629533886909485},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.42882055044174194},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.42673659324645996},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3202856481075287},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3334480.3382949","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3334480.3382949","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Extended Abstracts of the 2020 CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W342829753","https://openalex.org/W2001653897","https://openalex.org/W2021097538","https://openalex.org/W2022588856","https://openalex.org/W2024633545","https://openalex.org/W2043354045","https://openalex.org/W2048261712","https://openalex.org/W2116808802","https://openalex.org/W2144935315","https://openalex.org/W2149252982","https://openalex.org/W2153579005","https://openalex.org/W2159452379","https://openalex.org/W2337002970","https://openalex.org/W2394762924","https://openalex.org/W2735369705","https://openalex.org/W2769358515","https://openalex.org/W2770661558","https://openalex.org/W2795975316","https://openalex.org/W2950018712","https://openalex.org/W2963108875","https://openalex.org/W2963366196","https://openalex.org/W2963667126","https://openalex.org/W3006210356"],"related_works":["https://openalex.org/W2367925007","https://openalex.org/W3015724364","https://openalex.org/W4288263119","https://openalex.org/W2967994095","https://openalex.org/W2900126711","https://openalex.org/W4285240985","https://openalex.org/W4225162083","https://openalex.org/W3202115945","https://openalex.org/W2542958340","https://openalex.org/W4389520438"],"abstract_inverted_index":{"Biases":[0],"in":[1,30],"data,":[2,80],"such":[3],"as":[4],"gender":[5],"and":[6,14,22],"racial":[7],"stereotypes,":[8,88],"are":[9],"propagated":[10],"through":[11],"intelligent":[12],"systems":[13],"amplified":[15],"at":[16],"end-user":[17],"applications.":[18],"Existing":[19],"studies":[20],"detect":[21,109],"quantify":[23,55,86],"biases":[24,57],"based":[25],"on":[26],"pre-defined":[27],"attributes.":[28],"However,":[29],"real":[31],"practices,":[32],"it":[33],"is":[34],"difficult":[35],"to":[36,54,108],"gather":[37],"a":[38,51,67,104],"comprehensive":[39],"list":[40],"of":[41,47,62,77],"sensitive":[42],"concepts":[43],"for":[44],"various":[45],"categories":[46],"biases.":[48,111],"We":[49],"propose":[50],"general":[52],"methodology":[53],"dataset":[56,69],"by":[58,98],"measuring":[59],"the":[60,75],"difference":[61],"its":[63],"data":[64],"distribution":[65],"with":[66],"reference":[68],"using":[70],"Maximum":[71],"Mean":[72],"Discrepancy.":[73],"For":[74],"case":[76],"natural":[78],"language":[79],"we":[81],"show":[82],"that":[83],"lexicon-based":[84],"features":[85,92],"explicit":[87],"while":[89],"deep":[90],"learning-based":[91],"further":[93],"capture":[94],"implicit":[95],"stereotypes":[96],"represented":[97],"complex":[99],"semantics.":[100],"Our":[101],"method":[102],"provides":[103],"more":[105],"flexible":[106],"way":[107],"potential":[110]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}