{"id":"https://openalex.org/W7126427640","doi":"https://doi.org/10.18653/v1/2024.law-1.6","title":"Towards Better Inclusivity: A Diverse Tweet Corpus of English Varieties","display_name":"Towards Better Inclusivity: A Diverse Tweet Corpus of English Varieties","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W7126427640","doi":"https://doi.org/10.18653/v1/2024.law-1.6"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2024.law-1.6","doi":"https://doi.org/10.18653/v1/2024.law-1.6","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.law-1.6","pdf_url":"https://aclanthology.org/2024.law-1.6.pdf","source":{"id":"https://openalex.org/S4306420465","display_name":"Linguistic Annotation Workshop","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 18th Linguistic Annotation Workshop (LAW-XVIII)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2024.law-1.6.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057877554","display_name":"Nhi Pham","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nhi Pham","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088278557","display_name":"Lachlan Pham","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lachlan Pham","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043134485","display_name":"Adam Meyers","orcid":"https://orcid.org/0000-0002-9226-9992","observed_orcids":["https://orcid.org/0000-0002-9226-9992"]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adam Meyers","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I57206974"],"apc_list":null,"apc_paid":null,"fwci":0.8662,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.77339396,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"61","last_page":"70"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.6294000148773193,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.6294000148773193,"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/T11640","display_name":"Linguistic Variation and Morphology","score":0.11410000175237656,"subfield":{"id":"https://openalex.org/subfields/3310","display_name":"Linguistics and Language"},"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/T13155","display_name":"Digital Communication and Language","score":0.08810000121593475,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/varieties-of-english","display_name":"English language varieties","score":0.8519999980926514},{"id":"https://openalex.org/keywords/hinglish","display_name":"Hinglish","score":0.7490000128746033},{"id":"https://openalex.org/keywords/singlish","display_name":"Singlish","score":0.9789999723434448},{"id":"https://openalex.org/keywords/african-american-english","display_name":"African American English","score":0.984000027179718},{"id":"https://openalex.org/keywords/twitter-corpus","display_name":"Twitter corpus","score":0.5839999914169312},{"id":"https://openalex.org/keywords/corpus-curation","display_name":"corpus curation","score":0.640999972820282},{"id":"https://openalex.org/keywords/annotation-framework","display_name":"annotation framework","score":0.5910000205039978}],"concepts":[{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5601000189781189},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4408999979496002},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38589999079704285},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38179999589920044},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.35089999437332153},{"id":"https://openalex.org/C2778575526","wikidata":"https://www.wikidata.org/wiki/Q2631145","display_name":"Varieties of English","level":2,"score":0.3224000036716461},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.31360000371932983},{"id":"https://openalex.org/C532629269","wikidata":"https://www.wikidata.org/wiki/Q865083","display_name":"Corpus linguistics","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.25119999051094055},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.25}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2024.law-1.6","doi":"https://doi.org/10.18653/v1/2024.law-1.6","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.law-1.6","pdf_url":"https://aclanthology.org/2024.law-1.6.pdf","source":{"id":"https://openalex.org/S4306420465","display_name":"Linguistic Annotation Workshop","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 18th Linguistic Annotation Workshop (LAW-XVIII)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2401.11487","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2401.11487","pdf_url":"https://arxiv.org/pdf/2401.11487","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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2401.11487","doi":"https://doi.org/10.48550/arxiv.2401.11487","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2401.11487","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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.law-1.6","doi":"https://doi.org/10.18653/v1/2024.law-1.6","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.law-1.6","pdf_url":"https://aclanthology.org/2024.law-1.6.pdf","source":{"id":"https://openalex.org/S4306420465","display_name":"Linguistic Annotation Workshop","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 18th Linguistic Annotation Workshop (LAW-XVIII)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7578999996185303,"id":"https://metadata.un.org/sdg/10"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7126427640.pdf","grobid_xml":"https://content.openalex.org/works/W7126427640.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3155965651","https://openalex.org/W2753894810","https://openalex.org/W4412888471","https://openalex.org/W2757188127","https://openalex.org/W4416070658","https://openalex.org/W2508354372","https://openalex.org/W7140127496","https://openalex.org/W4386566339","https://openalex.org/W7213384975","https://openalex.org/W4416034035"],"abstract_inverted_index":{"The":[0],"prevalence":[1],"of":[2,14,18,89,105,138,149,156,166,177,189],"social":[3,32],"media":[4,33],"presents":[5],"a":[6,38,46,66,147,171],"growing":[7],"opportunity":[8],"to":[9,42,68,115,134,185],"collect":[10],"and":[11,55,80,109,161,180,196],"analyse":[12],"examples":[13],"English":[15,50,53,57,84,98,158,179,190],"varieties.Whilst":[16],"usage":[17],"these":[19,90,193],"varieties":[20,64,107,191],"is":[21],"often":[22,77],"used":[23],"only":[24],"in":[25,45,192],"spoken":[26],"contexts":[27],"or":[28,129],"hard-to-access":[29],"private":[30],"messages,":[31],"sites":[34],"like":[35,126],"Twitter":[36],"provide":[37],"platform":[39],"for":[40,85,103],"users":[41,104],"communicate":[43],"informally":[44],"scrapeable":[47],"format.Notably,":[48],"Indian":[49],"(Hinglish),":[51],"Singaporean":[52],"(Singlish),":[54],"African-American":[56],"(AAE)":[58],"can":[59],"be":[60],"commonly":[61],"found":[62],"online.These":[63],"pose":[65],"challenge":[67],"existing":[69],"natural":[70],"language":[71],"processing":[72],"(NLP)":[73],"tools":[74,91],"as":[75],"they":[76],"differ":[78],"orthographically":[79],"syntactically":[81],"from":[82,151],"standard":[83,97,178],"which":[86],"the":[87,117,136,175,187],"majority":[88],"are":[92,198],"built.NLP":[93],"models":[94],"trained":[95],"on":[96,200],"texts":[99],"produced":[100],"biased":[101],"outcomes":[102],"underrepresented":[106],"(Blodgett":[108],"O'Connor,":[110],"2017).Some":[111],"research":[112],"has":[113],"aimed":[114],"overcome":[116],"inherent":[118],"biases":[119],"caused":[120],"by":[121],"unrepresentative":[122],"data":[123,127,144],"through":[124],"techniques":[125],"augmentation":[128],"adjusting":[130],"training":[131],"models.We":[132],"aim":[133],"address":[135],"issue":[137],"bias":[139],"at":[140],"its":[141],"root":[142],"-the":[143],"itself.We":[145],"curate":[146],"dataset":[148,197],"tweets":[150],"countries":[152],"with":[153],"high":[154],"proportions":[155],"underserved":[157],"variety":[159],"speakers,":[160],"propose":[162],"an":[163],"annotation":[164],"framework":[165],"six":[167],"categorical":[168],"classifications":[169],"along":[170],"pseudospectrum":[172],"that":[173,181],"measures":[174],"degree":[176],"thereby":[182],"indirectly":[183],"aims":[184],"surface":[186],"manifestations":[188],"tweets.The":[194],"code":[195],"available":[199],"phamleyennhi/diverse_english_corpus.":[201]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2026-02-02T00:00:00"}