{"id":"https://openalex.org/W3204432444","doi":"https://doi.org/10.18653/v1/2021.wnut-1.35","title":"Detecting Cross-Geographic Biases in Toxicity Modeling on Social Media","display_name":"Detecting Cross-Geographic Biases in Toxicity Modeling on Social Media","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3204432444","doi":"https://doi.org/10.18653/v1/2021.wnut-1.35","mag":"3204432444"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2021.wnut-1.35","doi":"https://doi.org/10.18653/v1/2021.wnut-1.35","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.wnut-1.35","pdf_url":"https://aclanthology.org/2021.wnut-1.35.pdf","source":{"id":"https://openalex.org/S7407088860","display_name":"Workshop on Noisy User-generated Text (W-NUT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Seventh Workshop on Noisy User-generated Text (W-NUT 2021)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2021.wnut-1.35.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100670911","display_name":"Sayan Ghosh","orcid":"https://orcid.org/0000-0001-8758-7657","observed_orcids":["https://orcid.org/0000-0001-8758-7657","https://orcid.org/0000-0002-6035-5984"]},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sayan Ghosh","raw_affiliation_strings":["University of Michigan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043392679","display_name":"Dylan Baker","orcid":"https://orcid.org/0000-0002-2468-2347","observed_orcids":["https://orcid.org/0000-0002-2468-2347"]},"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":"Dylan Baker","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046126345","display_name":"David Jurgens","orcid":"https://orcid.org/0000-0002-2135-9878","observed_orcids":["https://orcid.org/0000-0002-2135-9878"]},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Jurgens","raw_affiliation_strings":["University of Michigan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019297976","display_name":"Vinodkumar Prabhakaran","orcid":"https://orcid.org/0000-0003-3329-2305","observed_orcids":["https://orcid.org/0000-0003-3329-2305"]},"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":"Vinodkumar Prabhakaran","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5174,"has_fulltext":true,"cited_by_count":37,"citation_normalized_percentile":{"value":0.91517492,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":87,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"313","last_page":"328"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9994999766349792,"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":0.9994999766349792,"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":0.00019999999494757503,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.0,"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/toxicity-detection","display_name":"toxicity detection","score":0.9010000228881836},{"id":"https://openalex.org/keywords/lexical-bias","display_name":"lexical bias","score":0.5429999828338623},{"id":"https://openalex.org/keywords/social-media","display_name":"social media","score":0.4880000054836273},{"id":"https://openalex.org/keywords/abusive-content-detection","display_name":"abusive content detection","score":0.5759999752044678},{"id":"https://openalex.org/keywords/marginalized-communities","display_name":"marginalized communities","score":0.8289999961853027},{"id":"https://openalex.org/keywords/bias-mitigation","display_name":"bias mitigation","score":0.7360000014305115},{"id":"https://openalex.org/keywords/training-data-bias","display_name":"training data bias","score":0.6330000162124634}],"concepts":[{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.8142439126968384},{"id":"https://openalex.org/C176856949","wikidata":"https://www.wikidata.org/wiki/Q2001676","display_name":"Offensive","level":2,"score":0.7295092344284058},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6678188443183899},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.5956012010574341},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5581284761428833},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5527792572975159},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.5282040238380432},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48327428102493286},{"id":"https://openalex.org/C130440534","wikidata":"https://www.wikidata.org/wiki/Q14946528","display_name":"Conflation","level":2,"score":0.46167799830436707},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.423348605632782},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37151843309402466},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.15911632776260376},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.13795459270477295},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12036347389221191},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.09550294280052185},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.18653/v1/2021.wnut-1.35","doi":"https://doi.org/10.18653/v1/2021.wnut-1.35","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.wnut-1.35","pdf_url":"https://aclanthology.org/2021.wnut-1.35.pdf","source":{"id":"https://openalex.org/S7407088860","display_name":"Workshop on Noisy User-generated Text (W-NUT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Seventh Workshop on Noisy User-generated Text (W-NUT 2021)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2104.06999","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.06999","pdf_url":"https://arxiv.org/pdf/2104.06999","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3156136792","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2104.06999","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2104.06999","doi":"https://doi.org/10.48550/arxiv.2104.06999","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2104.06999","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"mag:3213889377","doi":null,"is_oa":false,"landing_page_url":"https://aclanthology.org/2021.wnut-1.35/","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"doi:10.18653/v1/2021.wnut-1.35","doi":"https://doi.org/10.18653/v1/2021.wnut-1.35","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.wnut-1.35","pdf_url":"https://aclanthology.org/2021.wnut-1.35.pdf","source":{"id":"https://openalex.org/S7407088860","display_name":"Workshop on Noisy User-generated Text (W-NUT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Seventh Workshop on Noisy User-generated Text (W-NUT 2021)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.8974000215530396,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320882","display_name":"Volkswagen Foundation","ror":"https://ror.org/03bsmfz84"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3204432444.pdf","grobid_xml":"https://content.openalex.org/works/W3204432444.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W2038411619","https://openalex.org/W2073443734","https://openalex.org/W2143017621","https://openalex.org/W2473555522","https://openalex.org/W2563826943","https://openalex.org/W2594590228","https://openalex.org/W2595653137","https://openalex.org/W2761999826","https://openalex.org/W2769358515","https://openalex.org/W2791170418","https://openalex.org/W2888167352","https://openalex.org/W2889016530","https://openalex.org/W2890059736","https://openalex.org/W2893240881","https://openalex.org/W2893425640","https://openalex.org/W2896457183","https://openalex.org/W2902799923","https://openalex.org/W2920807444","https://openalex.org/W2921834779","https://openalex.org/W2922862135","https://openalex.org/W2947838315","https://openalex.org/W2949678053","https://openalex.org/W2951737564","https://openalex.org/W2952038496","https://openalex.org/W2953320089","https://openalex.org/W2963341956","https://openalex.org/W2970723691","https://openalex.org/W2972413484","https://openalex.org/W2972539067","https://openalex.org/W2978017171","https://openalex.org/W2993013587","https://openalex.org/W2996440722","https://openalex.org/W3013741514","https://openalex.org/W3015360426","https://openalex.org/W3019416653","https://openalex.org/W3035296331","https://openalex.org/W3094180864","https://openalex.org/W3099950438","https://openalex.org/W3113269238","https://openalex.org/W3123871787","https://openalex.org/W3155742828"],"related_works":["https://openalex.org/W3156136792","https://openalex.org/W4200325561","https://openalex.org/W4385573886","https://openalex.org/W3184088840","https://openalex.org/W7131220082","https://openalex.org/W3155742828","https://openalex.org/W4404782596","https://openalex.org/W7131875891","https://openalex.org/W7204175496","https://openalex.org/W4317536030"],"abstract_inverted_index":{"Online":[0],"social":[1],"media":[2],"platforms":[3],"increasingly":[4],"rely":[5],"on":[6,47,59,66,110,156],"Natural":[7],"Language":[8],"Processing":[9],"(NLP)":[10],"techniques":[11,30],"to":[12,20,26,50,98,163],"detect":[13,100],"abusive":[14],"content":[15,48],"at":[16],"scale":[17],"in":[18,39,44,87,103,129,145],"order":[19],"mitigate":[21],"the":[22,88],"harms":[23,56],"it":[24],"causes":[25],"their":[27],"users.However,":[28],"these":[29,135,166],"suffer":[31],"from":[32],"various":[33],"sampling":[34],"and":[35,74,142,168],"association":[36],"biases":[37,61,80,102],"present":[38,169],"training":[40],"data,":[41],"often":[42],"resulting":[43],"sub-par":[45],"performance":[46],"relevant":[49],"marginalized":[51],"groups,":[52],"potentially":[53],"furthering":[54],"disproportionate":[55],"towards":[57],"them.Studies":[58],"such":[60],"so":[62],"far":[63],"have":[64,77],"focused":[65],"only":[67],"a":[68,94,107,111,130,153,157],"handful":[69],"of":[70,72,125,140,152],"axes":[71],"disparities":[73],"subgroups":[75],"that":[76,119,134],"annotations/lexicons":[78],"available.Consequently,":[79],"concerning":[81],"non-Western":[82],"contexts":[83],"are":[84],"largely":[85],"ignored":[86],"literature.In":[89],"this":[90],"paper,":[91],"we":[92,117],"introduce":[93],"weakly":[95],"supervised":[96],"method":[97,121],"robustly":[99],"lexical":[101],"broader":[104],"geocultural":[105],"contexts.Through":[106],"case":[108],"study":[109],"publicly":[112],"available":[113],"toxicity":[114],"detection":[115],"model,":[116],"demonstrate":[118,133],"our":[120],"identifies":[122],"salient":[123],"groups":[124],"cross-geographic":[126],"errors,":[127],"and,":[128],"follow":[131],"up,":[132],"groupings":[136],"reflect":[137],"human":[138],"judgments":[139],"offensive":[141],"inoffensive":[143],"language":[144],"those":[146],"geographic":[147],"contexts.We":[148],"also":[149],"conduct":[150],"analysis":[151],"model":[154],"trained":[155],"dataset":[158],"with":[159],"ground":[160],"truth":[161],"labels":[162],"better":[164],"understand":[165],"biases,":[167],"preliminary":[170],"mitigation":[171],"experiments.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":1}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2021-10-11T00:00:00"}