{"id":"https://openalex.org/W6968739914","doi":"https://doi.org/10.5281/zenodo.16529721","title":"EsCorpiusBias: Contextual Annotation and Transformer-Based Detection of Racism and Sexism in Spanish Dialogues","display_name":"EsCorpiusBias: Contextual Annotation and Transformer-Based Detection of Racism and Sexism in Spanish Dialogues","publication_year":2025,"publication_date":"2025-07-28","ids":{"openalex":"https://openalex.org/W6968739914","doi":"https://doi.org/10.5281/zenodo.16529721"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.16529721","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.16529721","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"Dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.16529721","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Kharitonova, Ksenia","orcid":"https://orcid.org/0000-0002-9139-2622"},"institutions":[{"id":"https://openalex.org/I173304897","display_name":"Universidad de Granada","ror":"https://ror.org/04njjy449","country_code":"ES","type":"education","lineage":["https://openalex.org/I173304897"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Kharitonova, Ksenia","raw_affiliation_strings":["Universidad de Granada"],"raw_orcid":"https://orcid.org/0000-0002-9139-2622","affiliations":[{"raw_affiliation_string":"Universidad de Granada","institution_ids":["https://openalex.org/I173304897"]}]},{"author_position":"middle","author":{"id":null,"display_name":"P\u00e9rez Fern\u00e1ndez, David","orcid":"https://orcid.org/0000-0002-2214-0245"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"P\u00e9rez Fern\u00e1ndez, David","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-2214-0245","affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Guti\u00e9rrez-Hernando, Javier","orcid":null},"institutions":[{"id":"https://openalex.org/I173304897","display_name":"Universidad de Granada","ror":"https://ror.org/04njjy449","country_code":"ES","type":"education","lineage":["https://openalex.org/I173304897"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Guti\u00e9rrez-Hernando, Javier","raw_affiliation_strings":["Universidad de Granada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidad de Granada","institution_ids":["https://openalex.org/I173304897"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Guti\u00e9rrez-Fandi\u00f1o, Asier","orcid":"https://orcid.org/0000-0002-7368-6950"},"institutions":[{"id":"https://openalex.org/I1283111495","display_name":"Ministry of Economy","ror":"https://ror.org/021p8a188","country_code":"MK","type":"government","lineage":["https://openalex.org/I1283111495"]},{"id":"https://openalex.org/I1330693074","display_name":"Walmart (United States)","ror":"https://ror.org/04j0gge90","country_code":"US","type":"company","lineage":["https://openalex.org/I1330693074"]},{"id":"https://openalex.org/I88060688","display_name":"Universidad Polit\u00e9cnica de Madrid","ror":"https://ror.org/03n6nwv02","country_code":"ES","type":"education","lineage":["https://openalex.org/I88060688"]}],"countries":["ES","MK","US"],"is_corresponding":false,"raw_author_name":"Guti\u00e9rrez-Fandi\u00f1o, Asier","raw_affiliation_strings":["Universidad Polit\u00e9cnica de Madrid - Campus Sur","Walmart (United States)","Spanish Ministry of Economy"],"raw_orcid":"https://orcid.org/0000-0002-7368-6950","affiliations":[{"raw_affiliation_string":"Universidad Polit\u00e9cnica de Madrid - Campus Sur","institution_ids":["https://openalex.org/I88060688"]},{"raw_affiliation_string":"Walmart (United States)","institution_ids":["https://openalex.org/I1330693074"]},{"raw_affiliation_string":"Spanish Ministry of Economy","institution_ids":["https://openalex.org/I1283111495"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Callejas, Zoraida","orcid":"https://orcid.org/0000-0001-8891-5237"},"institutions":[{"id":"https://openalex.org/I173304897","display_name":"Universidad de Granada","ror":"https://ror.org/04njjy449","country_code":"ES","type":"education","lineage":["https://openalex.org/I173304897"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Callejas, Zoraida","raw_affiliation_strings":["Universidad de Granada"],"raw_orcid":"https://orcid.org/0000-0001-8891-5237","affiliations":[{"raw_affiliation_string":"Universidad de Granada","institution_ids":["https://openalex.org/I173304897"]}]},{"author_position":"last","author":{"id":null,"display_name":"Griol, David","orcid":"https://orcid.org/0000-0001-6266-5321"},"institutions":[{"id":"https://openalex.org/I173304897","display_name":"Universidad de Granada","ror":"https://ror.org/04njjy449","country_code":"ES","type":"education","lineage":["https://openalex.org/I173304897"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Griol, David","raw_affiliation_strings":["Universidad de Granada"],"raw_orcid":"https://orcid.org/0000-0001-6266-5321","affiliations":[{"raw_affiliation_string":"Universidad de Granada","institution_ids":["https://openalex.org/I173304897"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.7789000272750854},{"id":"https://openalex.org/keywords/racism","display_name":"Racism","score":0.5633999705314636},{"id":"https://openalex.org/keywords/moderation","display_name":"Moderation","score":0.5285999774932861},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5045999884605408},{"id":"https://openalex.org/keywords/crowdsourcing","display_name":"Crowdsourcing","score":0.3781000077724457},{"id":"https://openalex.org/keywords/computational-linguistics","display_name":"Computational linguistics","score":0.3034000098705292},{"id":"https://openalex.org/keywords/lexical-access","display_name":"Lexical access","score":0.29660001397132874}],"concepts":[{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.7789000272750854},{"id":"https://openalex.org/C139838865","wikidata":"https://www.wikidata.org/wiki/Q8461","display_name":"Racism","level":2,"score":0.5633999705314636},{"id":"https://openalex.org/C93225998","wikidata":"https://www.wikidata.org/wiki/Q1941972","display_name":"Moderation","level":2,"score":0.5285999774932861},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5045999884605408},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4871000051498413},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4602999985218048},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.42750000953674316},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4106999933719635},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.3781000077724457},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3716999888420105},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.36410000920295715},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.3034000098705292},{"id":"https://openalex.org/C2987487971","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexical access","level":3,"score":0.29660001397132874},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.2822999954223633},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.2757999897003174},{"id":"https://openalex.org/C85973986","wikidata":"https://www.wikidata.org/wiki/Q1091731","display_name":"Exploratory research","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C84389358","wikidata":"https://www.wikidata.org/wiki/Q1129466","display_name":"Discourse analysis","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.25609999895095825},{"id":"https://openalex.org/C143095724","wikidata":"https://www.wikidata.org/wiki/Q515895","display_name":"Odds","level":3,"score":0.2551000118255615}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.16529721","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.16529721","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"doi:10.5281/zenodo.16529721","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.16529721","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"Dataset"},"sustainable_development_goals":[{"score":0.7243963479995728,"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality"}],"awards":[{"id":"https://openalex.org/G2713626083","display_name":null,"funder_award_id":"TED2021-132470B-I00","funder_id":"https://openalex.org/F4320315062","funder_display_name":"Ministerio de Ciencia, Innovaci\u00f3n y Universidades"}],"funders":[{"id":"https://openalex.org/F4320315062","display_name":"Ministerio de Ciencia, Innovaci\u00f3n y Universidades","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0,74],"rise":[1],"of":[2,33,49,69,86,163,172],"online":[3,39,187],"communication":[4],"platforms":[5],"has":[6,63],"significantly":[7,134],"increased":[8],"exposure":[9],"to":[10,29,101,179],"harmful":[11],"discourse,":[12],"presenting":[13],"ongoing":[14],"challenges":[15],"for":[16,108,111,168],"digital":[17],"moderation":[18],"and":[19,35,71,83,88,90,122,127,137,177],"user":[20],"well-being.":[21],"This":[22,158],"paper":[23],"introduces":[24],"the":[25,44,95,161],"EsCorpiusBias":[26],"corpus,":[27],"designed":[28],"enhance":[30],"automated":[31,170],"detection":[32,171],"sexism":[34,87],"racism":[36],"within":[37,185],"Spanish-language":[38],"dialogues,":[40],"specifically":[41],"sourced":[42],"from":[43],"Mediavida":[45],"forum.":[46],"By":[47],"means":[48],"a":[50,145],"systematic,":[51],"context-sensitive":[52],"annotation":[53,75],"protocol,":[54],"approximately":[55],"1,000":[56],"three-turn":[57],"dialogue":[58],"units":[59],"per":[60],"bias":[61],"category":[62],"been":[64,78],"annotated,":[65],"ensuring":[66],"nuanced":[67],"recognition":[68],"pragmatic":[70],"conversational":[72],"subtleties.":[73],"guidelines":[76],"have":[77],"meticulously":[79],"developed,":[80],"covering":[81],"explicit":[82,149],"implicit":[84,156],"manifestations":[85],"racism,":[89],"annotations":[91],"were":[92,125],"performed":[93],"using":[94],"Prodigy":[96],"tool,":[97],"resulting":[98],"in":[99,154],"moderate":[100],"substantial":[102],"inter-annotator":[103],"agreement":[104],"(Cohen's":[105],"Kappa:":[106],"0.55":[107],"sexism,":[109],"0.79":[110],"racism).":[112],"Models":[113],"including":[114],"Logistic":[115],"Regression,":[116],"SpaCy's":[117],"baseline":[118,136],"n-gram":[119],"bag-of-words":[120],"model,":[121],"transformer-based":[123,132],"BETO":[124],"trained":[126],"evaluated,":[128],"demonstrating":[129],"that":[130],"contextualized":[131],"approaches":[133],"outperform":[135],"general-purpose":[138],"models.":[139],"Additionally,":[140],"lexical":[141,150],"overlap":[142],"analyses":[143],"indicated":[144],"strong":[146],"reliance":[147],"on":[148],"indicators,":[151],"highlighting":[152],"limitations":[153],"handling":[155],"biases.":[157],"research":[159],"underscores":[160],"importance":[162],"contextually":[164],"grounded,":[165],"domain-specific":[166],"fine-tuning":[167],"effective":[169],"toxicity,":[173],"providing":[174],"robust":[175],"resources":[176],"methodologies":[178],"foster":[180],"socially":[181],"responsible":[182],"NLP":[183],"systems":[184],"Spanish-speaking":[186],"communities.":[188]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}
