{"id":"https://openalex.org/W7104389960","doi":"https://doi.org/10.18653/v1/2025.nlperspectives-1.1","title":"A Disaggregated Dataset on English Offensiveness Containing Spans","display_name":"A Disaggregated Dataset on English Offensiveness Containing Spans","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W7104389960","doi":"https://doi.org/10.18653/v1/2025.nlperspectives-1.1"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.nlperspectives-1.1","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.nlperspectives-1.1","pdf_url":"https://aclanthology.org/2025.nlperspectives-1.1.pdf","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 The 4th Workshop on Perspectivist Approaches to NLP","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.nlperspectives-1.1.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Pia Pachinger","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pia Pachinger","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Janis Goldzycher","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Janis Goldzycher","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Anna M. Planitzer","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anna M. Planitzer","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Julia Neidhardt","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Julia Neidhardt","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Allan Hanbury","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Allan Hanbury","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":"1","last_page":"14"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.7299000024795532,"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":0.7299000024795532,"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/T11644","display_name":"Spam and Phishing Detection","score":0.07119999825954437,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.029500000178813934,"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/feature","display_name":"Feature (linguistics)","score":0.27250000834465027},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.24660000205039978},{"id":"https://openalex.org/keywords/statistical-analysis","display_name":"Statistical analysis","score":0.23479999601840973},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.2312999963760376},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.21819999814033508}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.42669999599456787},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3052999973297119},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26249998807907104},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.24660000205039978},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.24529999494552612},{"id":"https://openalex.org/C2986587452","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical analysis","level":2,"score":0.23479999601840973},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2312999963760376},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.21819999814033508},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.2176000028848648}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2025.nlperspectives-1.1","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.nlperspectives-1.1","pdf_url":"https://aclanthology.org/2025.nlperspectives-1.1.pdf","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 The 4th Workshop on Perspectivist Approaches to NLP","raw_type":"proceedings-article"},{"id":"pmh:doi:10.5167/uzh-292784","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"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":"ConferenceItem"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.nlperspectives-1.1","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.nlperspectives-1.1","pdf_url":"https://aclanthology.org/2025.nlperspectives-1.1.pdf","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 The 4th Workshop on Perspectivist Approaches to NLP","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321003","display_name":"Vienna Science and Technology Fund","ror":"https://ror.org/01f9mc681"},{"id":"https://openalex.org/F4320323591","display_name":"Christian Doppler Forschungsgesellschaft","ror":"https://ror.org/00mv8h305"},{"id":"https://openalex.org/F4320323874","display_name":"Universit\u00e4t Z\u00fcrich","ror":"https://ror.org/02crff812"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7104389960.pdf","grobid_xml":"https://content.openalex.org/works/W7104389960.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Toxicity":[0],"labels":[1,7,36],"at":[2],"sub-document":[3],"granularity":[4],"and":[5,12,16,32,37,43,60,68],"disaggregated":[6,34],"lead":[8],"to":[9,157],"more":[10,150],"nuanced":[11],"personalized":[13],"toxicity":[14,35,88],"classification":[15],"facilitate":[17],"analysis.We":[18],"re-annotate":[19],"a":[20,106],"subset":[21],"of":[22,25,45,86,96,109],"1983":[23],"posts":[24,156],"the":[26,161,165],"Jigsaw":[27],"Toxic":[28],"Comment":[29],"Classification":[30],"Challenge":[31],"provide":[33],"spans":[38],"that":[39,50,69,123,143],"identify":[40],"inappropriate":[41,110,126],"language":[42,111],"targets":[44,101],"toxic":[46,97],"statements.Manual":[47],"analysis":[48],"shows":[49],"five":[51],"annotations":[52,163],"per":[53],"instance":[54],"effectively":[55,138],"capture":[56],"meaningful":[57],"disagreement":[58,67],"patterns":[59],"allow":[61],"for":[62,155],"finer":[63],"distinctions":[64],"between":[65],"genuine":[66],"arising":[70],"from":[71,83,140],"annotation":[72],"error":[73],"or":[74],"inconsistency.Our":[75],"main":[76],"findings":[77],"are:":[78],"(1)":[79],"Disagreement":[80,90,103],"often":[81],"stems":[82],"divergent":[84],"interpretations":[85],"edgecase":[87],"(2)":[89],"is":[91],"especially":[92],"high":[93],"in":[94,127,133],"cases":[95],"statements":[98],"involving":[99],"nonhuman":[100],"(3)":[102],"on":[104,115,121],"whether":[105],"passage":[107],"consists":[108],"occurs":[112],"not":[113],"only":[114],"inherently":[116],"questionable":[117],"terms,":[118],"but":[119],"also":[120],"words":[122],"may":[124],"be":[125,158],"specific":[128],"contexts":[129],"while":[130],"remaining":[131],"acceptable":[132],"others":[134],"(4)":[135],"Transformer-based":[136],"models":[137],"learn":[139],"aggregated":[141],"data":[142],"reduces":[144],"false":[145],"negative":[146],"classifications":[147],"by":[148],"being":[149],"sensitive":[151],"towards":[152],"minority":[153],"opinions":[154],"toxic.We":[159],"publish":[160],"new":[162],"under":[164],"CC":[166],"BY":[167],"4.0":[168],"license.":[169]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-08T00:00:00"}