{"id":"https://openalex.org/W4417122938","doi":"https://doi.org/10.1145/3811242.3819100","title":"How do datasets, developers, and models affect biases in a low-resourced language?: The Case of the Bengali Language","display_name":"How do datasets, developers, and models affect biases in a low-resourced language?: The Case of the Bengali Language","publication_year":2026,"publication_date":"2026-07-23","ids":{"openalex":"https://openalex.org/W4417122938","doi":"https://doi.org/10.1145/3811242.3819100"},"language":"en","primary_location":{"id":"doi:10.1145/3811242.3819100","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3811242.3819100","pdf_url":null,"source":null,"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 2026 ACM SIGCAS/SIGCHI Conference on Computing and Sustainable Societies","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3811242.3819100","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001567136","display_name":"Dipto Das","orcid":"https://orcid.org/0000-0001-5704-8804"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Dipto Das","raw_affiliation_strings":["Department of Computer Science, University of Toronto, Toronto, Ontario, Canada"],"raw_orcid":"https://orcid.org/0000-0001-5704-8804","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Toronto, Toronto, Ontario, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100659941","display_name":"Shion Guha","orcid":"https://orcid.org/0000-0003-0073-2378"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Shion Guha","raw_affiliation_strings":["Faculty of Information, University of Toronto, Toronto, Ontario, Canada"],"raw_orcid":"https://orcid.org/0000-0003-0073-2378","affiliations":[{"raw_affiliation_string":"Faculty of Information, University of Toronto, Toronto, Ontario, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048101000","display_name":"Bryan Semaan","orcid":"https://orcid.org/0000-0003-1151-2389"},"institutions":[{"id":"https://openalex.org/I188538660","display_name":"University of Colorado Boulder","ror":"https://ror.org/02ttsq026","country_code":"US","type":"education","lineage":["https://openalex.org/I188538660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bryan Semaan","raw_affiliation_strings":["Department of Information Science, University of Colorado Boulder, Boulder, Colorado, USA"],"raw_orcid":"https://orcid.org/0000-0003-1151-2389","affiliations":[{"raw_affiliation_string":"Department of Information Science, University of Colorado Boulder, Boulder, Colorado, USA","institution_ids":["https://openalex.org/I188538660"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"340","last_page":"357"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13194","display_name":"ICT in Developing Communities","score":0.28700000047683716,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T13194","display_name":"ICT in Developing Communities","score":0.28700000047683716,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.10130000114440918,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"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/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.07590000331401825,"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/sociotechnical-system","display_name":"Sociotechnical system","score":0.6190999746322632},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5864999890327454},{"id":"https://openalex.org/keywords/bengali","display_name":"Bengali","score":0.5317000150680542},{"id":"https://openalex.org/keywords/audit","display_name":"Audit","score":0.4966000020503998},{"id":"https://openalex.org/keywords/affect","display_name":"Affect (linguistics)","score":0.47209998965263367},{"id":"https://openalex.org/keywords/computational-sociology","display_name":"Computational sociology","score":0.43810001015663147},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4174000024795532}],"concepts":[{"id":"https://openalex.org/C127627568","wikidata":"https://www.wikidata.org/wiki/Q1639361","display_name":"Sociotechnical system","level":2,"score":0.6190999746322632},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5864999890327454},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5548999905586243},{"id":"https://openalex.org/C19235068","wikidata":"https://www.wikidata.org/wiki/Q9610","display_name":"Bengali","level":2,"score":0.5317000150680542},{"id":"https://openalex.org/C199521495","wikidata":"https://www.wikidata.org/wiki/Q181487","display_name":"Audit","level":2,"score":0.4966000020503998},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4754999876022339},{"id":"https://openalex.org/C2776035688","wikidata":"https://www.wikidata.org/wiki/Q1606558","display_name":"Affect (linguistics)","level":2,"score":0.47209998965263367},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4595000147819519},{"id":"https://openalex.org/C126349790","wikidata":"https://www.wikidata.org/wiki/Q905036","display_name":"Computational sociology","level":2,"score":0.43810001015663147},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.43529999256134033},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.41749998927116394},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4174000024795532},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.399399995803833},{"id":"https://openalex.org/C66402592","wikidata":"https://www.wikidata.org/wiki/Q2271421","display_name":"Sentiment analysis","level":2,"score":0.3953000009059906},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.38199999928474426},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.37560001015663147},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3197000026702881},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.31139999628067017},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.30079999566078186},{"id":"https://openalex.org/C76188268","wikidata":"https://www.wikidata.org/wiki/Q1783165","display_name":"Context effect","level":3,"score":0.28619998693466187},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.27549999952316284},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2732999920845032},{"id":"https://openalex.org/C98447023","wikidata":"https://www.wikidata.org/wiki/Q1540351","display_name":"Social identity theory","level":3,"score":0.25270000100135803}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3811242.3819100","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3811242.3819100","pdf_url":null,"source":null,"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 2026 ACM SIGCAS/SIGCHI Conference on Computing and Sustainable Societies","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.06816","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.06816","pdf_url":"https://arxiv.org/pdf/2506.06816","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:arXiv.org:2506.06816","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2506.06816","pdf_url":"https://arxiv.org/pdf/2506.06816","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,"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":"doi:10.48550/arxiv.2506.06816","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.06816","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,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1145/3811242.3819100","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3811242.3819100","pdf_url":null,"source":null,"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 2026 ACM SIGCAS/SIGCHI Conference on Computing and Sustainable Societies","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Sociotechnical":[0],"systems,":[1],"such":[2,51],"as":[3],"language":[4,32],"technologies,":[5],"frequently":[6],"exhibit":[7,101],"identity-based":[8],"biases.":[9],"These":[10],"biases":[11,102],"exacerbate":[12],"the":[13,48,117,140],"experiences":[14],"of":[15,50,72],"historically":[16],"marginalized":[17],"communities":[18],"and":[19,27,56,79,112,119,126,148],"remain":[20],"understudied":[21],"in":[22,59,151],"low-resource":[23],"contexts.":[24],"While":[25],"models":[26,75,100,125],"datasets":[28,90,127],"specific":[29],"to":[30,40,139],"a":[31,61],"or":[33],"with":[34],"multilingual":[35],"support":[36],"are":[37],"commonly":[38],"recommended":[39],"address":[41],"these":[42,137],"biases,":[43],"this":[44],"paper":[45],"empirically":[46],"tests":[47],"effectiveness":[49],"approaches":[52],"for":[53],"gender,":[54],"religion,":[55],"nationality-based":[57],"identities":[58],"Bengali,":[60],"widely":[62],"spoken":[63],"but":[64],"low-resourced":[65],"language.":[66],"We":[67,114,135],"conducted":[68],"an":[69],"algorithmic":[70,152],"audit":[71],"sentiment":[73,87],"analysis":[74,88],"built":[76],"on":[77,143],"mBERT":[78],"BanglaBERT,":[80],"which":[81],"were":[82],"fine-tuned":[83],"using":[84],"all":[85],"Bengali":[86],"(BSA)":[89],"from":[91,122,131],"Google":[92],"Dataset":[93],"Search.":[94],"Our":[95],"analyses":[96],"showed":[97],"that":[98],"BSA":[99],"across":[103],"different":[104],"identity":[105],"categories":[106],"despite":[107],"having":[108],"similar":[109],"semantic":[110],"content":[111],"structure.":[113],"also":[115],"examined":[116],"inconsistencies":[118],"uncertainties":[120],"arising":[121],"combining":[123],"pre-trained":[124],"created":[128],"by":[129],"individuals":[130],"diverse":[132],"demographic":[133],"backgrounds.":[134],"connected":[136],"findings":[138],"broader":[141],"discussions":[142],"epistemic":[144],"injustice,":[145],"AI":[146],"alignment,":[147],"methodological":[149],"decisions":[150],"audits.":[153]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}