{"id":"https://openalex.org/W2890727387","doi":"https://doi.org/10.18653/v1/w18-5102","title":"Hate Speech Dataset from a White Supremacy Forum","display_name":"Hate Speech Dataset from a White Supremacy Forum","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2890727387","doi":"https://doi.org/10.18653/v1/w18-5102","mag":"2890727387"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w18-5102","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-5102","pdf_url":"https://www.aclweb.org/anthology/W18-5102.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 2nd Workshop on Abusive Language Online (ALW2)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W18-5102.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002349953","display_name":"Ona de Gibert","orcid":null},"institutions":[{"id":"https://openalex.org/I4210092551","display_name":"Vicomtech","ror":"https://ror.org/0023sah13","country_code":"ES","type":"facility","lineage":["https://openalex.org/I4210092551"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Ona de Gibert","raw_affiliation_strings":["HSLT Group at Vicomtech, Donostia/San Sebastin, Spain"],"affiliations":[{"raw_affiliation_string":"HSLT Group at Vicomtech, Donostia/San Sebastin, Spain","institution_ids":["https://openalex.org/I4210092551"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072619061","display_name":"Naiara P\u00e9rez","orcid":"https://orcid.org/0000-0001-8648-0428"},"institutions":[{"id":"https://openalex.org/I4210092551","display_name":"Vicomtech","ror":"https://ror.org/0023sah13","country_code":"ES","type":"facility","lineage":["https://openalex.org/I4210092551"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Naiara Perez","raw_affiliation_strings":["HSLT Group at Vicomtech, Donostia/San Sebastin, Spain"],"affiliations":[{"raw_affiliation_string":"HSLT Group at Vicomtech, Donostia/San Sebastin, Spain","institution_ids":["https://openalex.org/I4210092551"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020366067","display_name":"Aitor Garc\u00eda Pablos","orcid":"https://orcid.org/0000-0001-9882-7521"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aitor Garc\u00eda-Pablos","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5073920793","display_name":"Montse Cuadros","orcid":"https://orcid.org/0000-0002-3620-1053"},"institutions":[{"id":"https://openalex.org/I4210092551","display_name":"Vicomtech","ror":"https://ror.org/0023sah13","country_code":"ES","type":"facility","lineage":["https://openalex.org/I4210092551"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Montse Cuadros","raw_affiliation_strings":["HSLT Group at Vicomtech, Donostia/San Sebastin, Spain"],"affiliations":[{"raw_affiliation_string":"HSLT Group at Vicomtech, Donostia/San Sebastin, Spain","institution_ids":["https://openalex.org/I4210092551"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5002349953"],"corresponding_institution_ids":["https://openalex.org/I4210092551"],"apc_list":null,"apc_paid":null,"fwci":2.3693,"has_fulltext":true,"cited_by_count":47,"citation_normalized_percentile":{"value":0.91362627,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"11","last_page":"20"},"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/T11598","display_name":"Internet Traffic Analysis and Secure E-voting","score":0.9520000219345093,"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":0.9215999841690063,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6661114692687988},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6180722117424011},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6106833815574646},{"id":"https://openalex.org/keywords/sexual-orientation","display_name":"Sexual orientation","score":0.5618025064468384},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5434785485267639},{"id":"https://openalex.org/keywords/crowd-sourcing","display_name":"Crowd sourcing","score":0.5429117679595947},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.49383291602134705},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.48374032974243164},{"id":"https://openalex.org/keywords/white","display_name":"White (mutation)","score":0.46314167976379395},{"id":"https://openalex.org/keywords/nationality","display_name":"Nationality","score":0.46024104952812195},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43513673543930054},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4163752794265747},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3366084694862366},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.23025447130203247},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.20767036080360413},{"id":"https://openalex.org/keywords/immigration","display_name":"Immigration","score":0.19530615210533142},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.18536999821662903},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.15020939707756042},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.08983522653579712}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6661114692687988},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6180722117424011},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6106833815574646},{"id":"https://openalex.org/C2777997956","wikidata":"https://www.wikidata.org/wiki/Q17888","display_name":"Sexual orientation","level":2,"score":0.5618025064468384},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5434785485267639},{"id":"https://openalex.org/C3018396927","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowd sourcing","level":2,"score":0.5429117679595947},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.49383291602134705},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.48374032974243164},{"id":"https://openalex.org/C56273599","wikidata":"https://www.wikidata.org/wiki/Q3122841","display_name":"White (mutation)","level":3,"score":0.46314167976379395},{"id":"https://openalex.org/C2777138209","wikidata":"https://www.wikidata.org/wiki/Q231002","display_name":"Nationality","level":3,"score":0.46024104952812195},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43513673543930054},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4163752794265747},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3366084694862366},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.23025447130203247},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.20767036080360413},{"id":"https://openalex.org/C70036468","wikidata":"https://www.wikidata.org/wiki/Q131288","display_name":"Immigration","level":2,"score":0.19530615210533142},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.18536999821662903},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.15020939707756042},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.08983522653579712},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/w18-5102","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-5102","pdf_url":"https://www.aclweb.org/anthology/W18-5102.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 2nd Workshop on Abusive Language Online (ALW2)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1809.04444","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1809.04444","pdf_url":"https://arxiv.org/pdf/1809.04444","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:2890727387","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1809.04444","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1809.04444","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1809.04444","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.18653/v1/w18-5102","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-5102","pdf_url":"https://www.aclweb.org/anthology/W18-5102.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 2nd Workshop on Abusive Language Online (ALW2)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5","score":0.5899999737739563}],"awards":[{"id":"https://openalex.org/G1103527585","display_name":"Analysis System for Gathered Raw Data","funder_award_id":"700381","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G3783317134","display_name":null,"funder_award_id":"H2020","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G4937468798","display_name":null,"funder_award_id":"H2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G5757424618","display_name":null,"funder_award_id":"700381","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320334779","display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","ror":"https://ror.org/00snfqn58"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2890727387.pdf","grobid_xml":"https://content.openalex.org/works/W2890727387.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W78136081","https://openalex.org/W80056832","https://openalex.org/W1689711448","https://openalex.org/W1871142974","https://openalex.org/W1975879668","https://openalex.org/W2008056655","https://openalex.org/W2032766435","https://openalex.org/W2340954483","https://openalex.org/W2563826943","https://openalex.org/W2585712495","https://openalex.org/W2604821579","https://openalex.org/W2740168486","https://openalex.org/W2741065173","https://openalex.org/W2757202410","https://openalex.org/W2773128093","https://openalex.org/W2792441346","https://openalex.org/W2807883874","https://openalex.org/W2947343938","https://openalex.org/W2951737564","https://openalex.org/W2953180101","https://openalex.org/W2962932155"],"related_works":["https://openalex.org/W3049698873","https://openalex.org/W3046087842","https://openalex.org/W2989798706","https://openalex.org/W2962993339","https://openalex.org/W3158468281","https://openalex.org/W3205253920","https://openalex.org/W3211864559","https://openalex.org/W2955194949","https://openalex.org/W2972735048","https://openalex.org/W2998366771","https://openalex.org/W3163488303","https://openalex.org/W2951804840","https://openalex.org/W3127753312","https://openalex.org/W2967734965","https://openalex.org/W3162264649","https://openalex.org/W2757188127","https://openalex.org/W2030139567","https://openalex.org/W1988931981","https://openalex.org/W2108441334","https://openalex.org/W1505422262"],"abstract_inverted_index":{"Hate":[0],"speech":[1,48,61,86,98],"is":[2,49,170],"commonly":[3],"defined":[4],"as":[5,20,95],"any":[6],"communication":[7],"that":[8],"disparages":[9],"a":[10,84,108,141,150],"target":[11],"group":[12],"of":[13,37,46,67,78,89,91,140,156],"people":[14],"based":[15],"on":[16,41],"some":[17],"characteristic":[18],"such":[19],"race,":[21],"colour,":[22],"ethnicity,":[23],"gender,":[24],"sexual":[25],"orientation,":[26],"nationality,":[27],"religion,":[28],"or":[29,99],"other":[30,128],"characteristic.":[31],"Due":[32],"to":[33,119,133,136],"the":[34,44,54,65,75,79,122,131,138,157],"massive":[35],"rise":[36],"user-generated":[38],"web":[39],"content":[40],"social":[42],"media,":[43],"amount":[45],"hate":[47,60,85,97],"also":[50,148],"steadily":[51],"increasing.":[52],"Over":[53],"past":[55],"years,":[56],"interest":[57],"in":[58],"online":[59],"detection":[62],"and,":[63],"particularly,":[64],"automation":[66],"this":[68],"task":[69,125],"has":[70,116],"continuously":[71],"grown,":[72],"along":[73],"with":[74,164],"societal":[76],"impact":[77],"phenomenon.":[80],"This":[81],"paper":[82,147],"describes":[83],"dataset":[87,159,169],"composed":[88],"thousands":[90],"sentences":[92,102],"manually":[93],"labelled":[94],"containing":[96],"not.":[100],"The":[101,146,168],"have":[103],"been":[104,117],"extracted":[105],"from":[106],"Stormfront,":[107],"white":[109],"supremacist":[110],"forum.":[111],"A":[112],"custom":[113],"annotation":[114],"tool":[115],"developed":[118],"carry":[120],"out":[121],"manual":[123],"labelling":[124,144],"which,":[126],"among":[127],"things,":[129],"allows":[130],"annotators":[132],"choose":[134],"whether":[135],"read":[137],"context":[139],"sentence":[142],"before":[143],"it.":[145],"provides":[149],"thoughtful":[151],"qualitative":[152],"and":[153,160],"quantitative":[154],"study":[155],"resulting":[158],"several":[161],"baseline":[162],"experiments":[163],"different":[165],"classification":[166],"models.":[167],"publicly":[171],"available.":[172]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
