{"id":"https://openalex.org/W4388486510","doi":"https://doi.org/10.1109/taslp.2023.3331139","title":"Factors That Influence Automatic Recognition of African-American Vernacular English in Machine-Learning Models","display_name":"Factors That Influence Automatic Recognition of African-American Vernacular English in Machine-Learning Models","publication_year":2023,"publication_date":"2023-11-08","ids":{"openalex":"https://openalex.org/W4388486510","doi":"https://doi.org/10.1109/taslp.2023.3331139"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3331139","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3331139","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5073144250","display_name":"Emma Hamel","orcid":"https://orcid.org/0000-0001-5400-8890"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Emma Hamel","raw_affiliation_strings":["Department of Computer Science, University of Illinois at Urbana-Champaign, Urbana, IL, USA"],"raw_orcid":"https://orcid.org/0000-0001-5400-8890","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021129244","display_name":"Nickvash Kani","orcid":"https://orcid.org/0000-0002-5223-5069"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nickvash Kani","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, Urbana, IL, USA"],"raw_orcid":"https://orcid.org/0000-0002-5223-5069","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":0.3173,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.63934107,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"32","issue":null,"first_page":"509","last_page":"516"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9983999729156494,"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":0.9983999729156494,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9983000159263611,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9959999918937683,"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/identification","display_name":"Identification (biology)","score":0.7107541561126709},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6965694427490234},{"id":"https://openalex.org/keywords/vernacular","display_name":"Vernacular","score":0.6603995561599731},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6098448038101196},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6096176505088806},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.5064812898635864},{"id":"https://openalex.org/keywords/american-english","display_name":"American English","score":0.48018279671669006},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4463822841644287},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4437640309333801},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3967442810535431},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3589703440666199},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33471983671188354},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3330819606781006},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10460612177848816},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.08693650364875793}],"concepts":[{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.7107541561126709},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6965694427490234},{"id":"https://openalex.org/C2780386941","wikidata":"https://www.wikidata.org/wiki/Q1036511","display_name":"Vernacular","level":2,"score":0.6603995561599731},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6098448038101196},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6096176505088806},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.5064812898635864},{"id":"https://openalex.org/C2777939226","wikidata":"https://www.wikidata.org/wiki/Q7976","display_name":"American English","level":2,"score":0.48018279671669006},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4463822841644287},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4437640309333801},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3967442810535431},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3589703440666199},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33471983671188354},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3330819606781006},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10460612177848816},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.08693650364875793},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2023.3331139","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3331139","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W57814663","https://openalex.org/W157108407","https://openalex.org/W1482098013","https://openalex.org/W1753184066","https://openalex.org/W2051811941","https://openalex.org/W2076330531","https://openalex.org/W2103661760","https://openalex.org/W2122637965","https://openalex.org/W2264054297","https://openalex.org/W2291776410","https://openalex.org/W2511234952","https://openalex.org/W2550576290","https://openalex.org/W2945976633","https://openalex.org/W2949678053","https://openalex.org/W2964235839","https://openalex.org/W2972735048","https://openalex.org/W2982448527","https://openalex.org/W2998366771","https://openalex.org/W3012624518","https://openalex.org/W3035377849","https://openalex.org/W3096755600","https://openalex.org/W3101004475","https://openalex.org/W3128232076","https://openalex.org/W3175765954","https://openalex.org/W3207352138","https://openalex.org/W4288086175","https://openalex.org/W4375869286","https://openalex.org/W6608110847","https://openalex.org/W6632118081","https://openalex.org/W6632865047","https://openalex.org/W6684503276","https://openalex.org/W6740019793"],"related_works":["https://openalex.org/W226586525","https://openalex.org/W1998541766","https://openalex.org/W2064542902","https://openalex.org/W2262900283","https://openalex.org/W1985349217","https://openalex.org/W2362145681","https://openalex.org/W2098508228","https://openalex.org/W2913520953","https://openalex.org/W1538826769","https://openalex.org/W2383292628"],"abstract_inverted_index":{"Racial":[0],"bias":[1,74],"is":[2,18],"a":[3,90,95,185],"well-documented":[4],"problem":[5],"in":[6,27,75,102,155],"natural":[7],"language":[8,13,24,41,76,170],"processing":[9],"(NLP).":[10],"The":[11,82],"dialectal":[12,112,153],"used":[14],"by":[15,23,196],"marginalized":[16],"groups":[17],"often":[19],"misclassified":[20],"or":[21],"mischaracterized":[22],"models,":[25],"which":[26,168],"turn":[28],"can":[29,106,189],"further":[30],"disenfranchise":[31],"these":[32,128],"populations.":[33],"Previous":[34],"works":[35],"have":[36],"noted":[37],"that":[38,50,60,70,94],"some":[39,169],"popular":[40],"identification":[42,171],"(LID)":[43],"models":[44,77,172],"perform":[45],"worse":[46],"when":[47,57,174],"classifying":[48,58,175],"tweets":[49,59],"contain":[51,61],"African-American":[52],"Vernacular":[53],"English":[54,63,154],"(AAVE)":[55],"than":[56],"White-Aligned":[62],"(WAE).":[64],"This":[65],"work":[66,86,131],"examines":[67],"the":[68,79,135,161,191],"factors":[69],"contribute":[71],"to":[72,108],"racial":[73],"for":[78,179],"LID":[80,104],"task.":[81],"contributions":[83],"of":[84,97,137,152],"this":[85,130],"are":[87],"two-fold.":[88],"First,":[89],"thorough":[91],"analysis":[92],"demonstrates":[93],"lack":[96],"\u201cunique\u201d":[98,145],"language-specific":[99],"n-gram":[100,146],"features":[101,147,181],"an":[103],"model":[105],"lead":[107],"poor":[109],"performance":[110],"on":[111,115,122,127,193],"data,":[113],"especially":[114],"shorter-length":[116],"inputs":[117],"like":[118],"those":[119],"typically":[120],"found":[121],"social":[123],"media.":[124],"Second,":[125],"based":[126],"findings,":[129],"introduces":[132],"and":[133,148,166,182,198],"illustrates":[134],"efficacy":[136],"two":[138],"simple":[139],"yet":[140],"accurate":[141],"solutions:":[142],"i.)":[143],"mining":[144],"ii.)":[149],"including":[150],"examples":[151],"training":[156,183],"data.":[157],"These":[158],"solutions":[159],"mitigate":[160],"accuracy":[162],"gap":[163],"between":[164],"WAE":[165],"AAVE":[167],"demonstrate":[173],"shorter":[176],"inputs.":[177],"Mining":[178],"unique":[180],"with":[184],"more":[186],"diverse":[187],"dataset":[188],"improve":[190],"disparity":[192],"short-length":[194],"sequences":[195],"6%":[197],"9.8%":[199],"respectively.":[200]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}