{"id":"https://openalex.org/W7140143473","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.100","title":"Nuanced Toxicity Detection in Spanish: A New Corpus and Benchmark Study","display_name":"Nuanced Toxicity Detection in Spanish: A New Corpus and Benchmark Study","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140143473","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.100"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.findings-eacl.100","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.100","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.100","pdf_url":"https://aclanthology.org/2026.findings-eacl.100.pdf","source":{"id":"https://openalex.org/S7407087051","display_name":"Findings of the Association for Computational Linguistics: EACL","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":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.findings-eacl.100.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5096943386","display_name":"Alba Mar\u00eda M\u00e1rmol-Romero","orcid":"https://orcid.org/0000-0001-7952-4541","observed_orcids":["https://orcid.org/0000-0001-7952-4541"]},"institutions":[{"id":"https://openalex.org/I191420491","display_name":"Universidad de Ja\u00e9n","ror":"https://ror.org/0122p5f64","country_code":"ES","type":"education","lineage":["https://openalex.org/I191420491"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Alba Mar\u00eda M\u00e1rmol-Romero","raw_affiliation_strings":["Computer Science Department , SINAI , CEATIC , University of Ja\u00e9n , Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department , SINAI , CEATIC , University of Ja\u00e9n , Spain","institution_ids":["https://openalex.org/I191420491"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004068410","display_name":"Robiert Sep\u00falveda-Torres","orcid":"https://orcid.org/0000-0002-2784-2748","observed_orcids":["https://orcid.org/0000-0002-2784-2748"]},"institutions":[{"id":"https://openalex.org/I130194489","display_name":"University of Alicante","ror":"https://ror.org/05t8bcz72","country_code":"ES","type":"education","lineage":["https://openalex.org/I130194489"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Robiert Sep\u00falveda-Torres","raw_affiliation_strings":["Department of Software and Computing Systems , University of Alicante , Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Software and Computing Systems , University of Alicante , Spain","institution_ids":["https://openalex.org/I130194489"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075246797","display_name":"Estela Saquete","orcid":"https://orcid.org/0000-0002-6001-5461","observed_orcids":["https://orcid.org/0000-0002-6001-5461"]},"institutions":[{"id":"https://openalex.org/I130194489","display_name":"University of Alicante","ror":"https://ror.org/05t8bcz72","country_code":"ES","type":"education","lineage":["https://openalex.org/I130194489"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Estela Saquete","raw_affiliation_strings":["Department of Software and Computing Systems , University of Alicante , Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Software and Computing Systems , University of Alicante , Spain","institution_ids":["https://openalex.org/I130194489"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130337860","display_name":"Mar\u00eda-Teresa Mart\u00edn-Valdivia","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I191420491","display_name":"Universidad de Ja\u00e9n","ror":"https://ror.org/0122p5f64","country_code":"ES","type":"education","lineage":["https://openalex.org/I191420491"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Mar\u00eda-Teresa Mart\u00edn-Valdivia","raw_affiliation_strings":["Computer Science Department , SINAI , CEATIC , University of Ja\u00e9n , Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department , SINAI , CEATIC , University of Ja\u00e9n , Spain","institution_ids":["https://openalex.org/I191420491"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016928206","display_name":"Lu\u00eds Alfonso Ure\u00f1a L\u00f3pez","orcid":"https://orcid.org/0000-0001-7540-4059","observed_orcids":["https://orcid.org/0000-0001-7540-4059"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"L. Alfonso Ure\u00f1a","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.9362,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.95389713,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1940","last_page":"1954"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":1.0,"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"}},{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":9.999999747378752e-05,"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/T10028","display_name":"Topic Modeling","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":0.8420000076293945},{"id":"https://openalex.org/keywords/spanish-language","display_name":"Spanish language","score":0.8960000276565552},{"id":"https://openalex.org/keywords/sarcasm-detection","display_name":"sarcasm detection","score":0.7900000214576721},{"id":"https://openalex.org/keywords/irony","display_name":"irony","score":0.7680000066757202},{"id":"https://openalex.org/keywords/indirect-aggression","display_name":"indirect aggression","score":0.8809999823570251},{"id":"https://openalex.org/keywords/annotation-protocol","display_name":"annotation protocol","score":0.5410000085830688},{"id":"https://openalex.org/keywords/inter-annotator-agreement","display_name":"inter-annotator agreement","score":0.9049999713897705},{"id":"https://openalex.org/keywords/instruction-tuned-large-language-models","display_name":"instruction-tuned large language models","score":0.8019999861717224},{"id":"https://openalex.org/keywords/roberta","display_name":"RoBERTa","score":0.7590000033378601},{"id":"https://openalex.org/keywords/news-comments","display_name":"news comments","score":0.5849999785423279},{"id":"https://openalex.org/keywords/data-anonymization","display_name":"data anonymization","score":0.9359999895095825}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6205000281333923},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6026999950408936},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5497999787330627},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4408999979496002},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36970001459121704},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28700000047683716},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2526000142097473},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-eacl.100","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.100","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.100","pdf_url":"https://aclanthology.org/2026.findings-eacl.100.pdf","source":{"id":"https://openalex.org/S7407087051","display_name":"Findings of the Association for Computational Linguistics: EACL","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":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-eacl.100","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.100","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.100","pdf_url":"https://aclanthology.org/2026.findings-eacl.100.pdf","source":{"id":"https://openalex.org/S7407087051","display_name":"Findings of the Association for Computational Linguistics: EACL","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":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"display_name":"Zero hunger","score":0.5172087550163269,"id":"https://metadata.un.org/sdg/2"}],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140143473.pdf","grobid_xml":"https://content.openalex.org/works/W7140143473.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4408819013","https://openalex.org/W4390953624","https://openalex.org/W7104389960","https://openalex.org/W7026786043","https://openalex.org/W7166505992","https://openalex.org/W3164720080","https://openalex.org/W4388275189","https://openalex.org/W3197822764","https://openalex.org/W3204236292","https://openalex.org/W4412698606"],"abstract_inverted_index":{"The":[0],"rise":[1],"of":[2,30,43,64,100,140,155],"toxic":[3],"content":[4],"on":[5,130],"digital":[6],"platforms":[7],"has":[8,17],"intensified":[9],"the":[10,44,104,138],"demand":[11],"for":[12,27],"automatic":[13],"moderation":[14],"tools.While":[15],"English":[16],"benefited":[18],"from":[19,53],"large-scale":[20],"annotated":[21,60],"corpora,":[22],"Spanish":[23,50],"remains":[24],"under-resourced,":[25],"particularly":[26],"nuanced":[28],"cases":[29],"toxicity":[31,65],"such":[32],"as":[33],"irony,":[34],"sarcasm,":[35],"or":[36],"indirect":[37],"aggression.We":[38],"present":[39],"an":[40,72],"extended":[41],"version":[42],"NECOS-TOX":[45],"corpus,":[46],"Social-Tox,":[47],"comprising":[48],"4,011":[49],"comments":[51],"collected":[52],"16":[54],"major":[55],"news":[56],"outlets.Each":[57],"comment":[58],"is":[59],"across":[61],"three":[62],"levels":[63],"(Non-Toxic,":[66],"Slightly":[67],"Toxic,":[68],"and":[69,114,159,162,171],"Toxic),":[70],"following":[71],"iterative":[73],"annotation":[74,85],"protocol":[75],"that":[76,121,166],"achieved":[77],"substantial":[78],"inter-annotator":[79],"agreement":[80],"(k":[81],"=":[82],"0.74).To":[83],"reduce":[84],"costs":[86],"while":[87],"maintaining":[88],"quality,":[89],"we":[90],"employed":[91],"a":[92],"humanin-the-loop":[93],"active":[94],"learning":[95,109],"strategy,":[96],"with":[97,106,132],"manual":[98],"correction":[99],"model":[101],"pre-labels.We":[102],"benchmarked":[103],"dataset":[105,170],"traditional":[107],"machine":[108],"(ML)":[110],"methods,":[111],"domain-specific":[112],"transformers,":[113],"instruction-tuned":[115],"large":[116],"language":[117],"models":[118,124,135,173],"(LLMs).Results":[119],"show":[120],"compact":[122],"encoder":[123],"(e.g.,":[125,136],"RoBERTa-base-bne,":[126],"125M":[127],"parameters)":[128],"perform":[129],"par":[131],"much":[133],"larger":[134],"LLaMA-3.1-8B),underscoring":[137],"value":[139],"in-domain":[141],"adaptation":[142],"over":[143],"raw":[144],"scale.Our":[145],"error":[146],"analysis":[147],"highlights":[148],"persistent":[149],"challenges":[150],"in":[151],"distinguishing":[152],"subtle":[153],"forms":[154],"toxicity,":[156],"especially":[157],"sarcasm":[158],"implicit":[160],"insults,":[161],"reveals":[163],"entity-related":[164],"biases":[165],"motivate":[167],"anonymization":[168],"strategies.The":[169],"trained":[172],"are":[174],"released":[175],"publicly.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-03-24T00:00:00"}