{"id":"https://openalex.org/W4415974163","doi":"https://doi.org/10.1016/j.procs.2025.09.480","title":"Tunisian Dialect Hate Speech and Abuse Detection with BERT-Based Models","display_name":"Tunisian Dialect Hate Speech and Abuse Detection with BERT-Based Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4415974163","doi":"https://doi.org/10.1016/j.procs.2025.09.480"},"language":"en","primary_location":{"id":"doi:10.1016/j.procs.2025.09.480","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.procs.2025.09.480","pdf_url":null,"source":{"id":"https://openalex.org/S120348307","display_name":"Procedia Computer Science","issn_l":"1877-0509","issn":["1877-0509"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Procedia Computer Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1016/j.procs.2025.09.480","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025538965","display_name":"Roua Torjmen","orcid":"https://orcid.org/0000-0003-0585-0795"},"institutions":[{"id":"https://openalex.org/I142899784","display_name":"University of Sfax","ror":"https://ror.org/04d4sd432","country_code":"TN","type":"education","lineage":["https://openalex.org/I142899784"]}],"countries":["TN"],"is_corresponding":true,"raw_author_name":"Roua Torjmen","raw_affiliation_strings":["Faculty of sciences of Sfax, University of Sfax, Road Sokra Km 3, 3018 Sfax, Tunisia"],"affiliations":[{"raw_affiliation_string":"Faculty of sciences of Sfax, University of Sfax, Road Sokra Km 3, 3018 Sfax, Tunisia","institution_ids":["https://openalex.org/I142899784"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010431834","display_name":"Kais Haddar","orcid":"https://orcid.org/0000-0002-5972-9694"},"institutions":[{"id":"https://openalex.org/I142899784","display_name":"University of Sfax","ror":"https://ror.org/04d4sd432","country_code":"TN","type":"education","lineage":["https://openalex.org/I142899784"]}],"countries":["TN"],"is_corresponding":false,"raw_author_name":"Kais Haddar","raw_affiliation_strings":["Faculty of sciences of Sfax, University of Sfax, Road Sokra Km 3, 3018 Sfax, Tunisia"],"affiliations":[{"raw_affiliation_string":"Faculty of sciences of Sfax, University of Sfax, Road Sokra Km 3, 3018 Sfax, Tunisia","institution_ids":["https://openalex.org/I142899784"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5025538965"],"corresponding_institution_ids":["https://openalex.org/I142899784"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18178373,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"270","issue":null,"first_page":"3548","last_page":"3557"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9853000044822693,"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":0.9853000044822693,"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":0.002199999988079071,"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":0.0012000000569969416,"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/focus","display_name":"Focus (optics)","score":0.6783000230789185},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.659600019454956},{"id":"https://openalex.org/keywords/modern-standard-arabic","display_name":"Modern Standard Arabic","score":0.5773000121116638},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.5169000029563904},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.5166000127792358},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.43070000410079956},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.33090001344680786},{"id":"https://openalex.org/keywords/standard-english","display_name":"Standard English","score":0.3215000033378601}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7971000075340271},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6783000230789185},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.659600019454956},{"id":"https://openalex.org/C2778243841","wikidata":"https://www.wikidata.org/wiki/Q56467","display_name":"Modern Standard Arabic","level":3,"score":0.5773000121116638},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.5169000029563904},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.5166000127792358},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5134999752044678},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.45559999346733093},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44839999079704285},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.43070000410079956},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.33090001344680786},{"id":"https://openalex.org/C2776630830","wikidata":"https://www.wikidata.org/wiki/Q14437894","display_name":"Standard English","level":2,"score":0.3215000033378601},{"id":"https://openalex.org/C2775957009","wikidata":"https://www.wikidata.org/wiki/Q399495","display_name":"Standard language","level":2,"score":0.3192000091075897},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.31869998574256897},{"id":"https://openalex.org/C171041071","wikidata":"https://www.wikidata.org/wiki/Q36870","display_name":"First language","level":2,"score":0.30970001220703125},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.2978000044822693},{"id":"https://openalex.org/C94922259","wikidata":"https://www.wikidata.org/wiki/Q33215","display_name":"Constructed language","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C3020202489","wikidata":"https://www.wikidata.org/wiki/Q2032038","display_name":"Authorship attribution","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C116081451","wikidata":"https://www.wikidata.org/wiki/Q1501364","display_name":"Language transfer","level":4,"score":0.2662999927997589},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.procs.2025.09.480","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.procs.2025.09.480","pdf_url":null,"source":{"id":"https://openalex.org/S120348307","display_name":"Procedia Computer Science","issn_l":"1877-0509","issn":["1877-0509"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Procedia Computer Science","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.procs.2025.09.480","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.procs.2025.09.480","pdf_url":null,"source":{"id":"https://openalex.org/S120348307","display_name":"Procedia Computer Science","issn_l":"1877-0509","issn":["1877-0509"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Procedia Computer Science","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1566256432","https://openalex.org/W2119821739","https://openalex.org/W2295598076","https://openalex.org/W2911964244","https://openalex.org/W2946417913","https://openalex.org/W2964199361","https://openalex.org/W2977739081","https://openalex.org/W3176169354","https://openalex.org/W3216821104","https://openalex.org/W4319078010","https://openalex.org/W4366674457","https://openalex.org/W4386207876","https://openalex.org/W4400117039","https://openalex.org/W4407058715","https://openalex.org/W4408325738"],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,169],"rapid":[2],"growth":[3],"of":[4,24,70],"social":[5],"media":[6],"platforms,":[7],"harmful":[8,45],"content":[9,25],"such":[10,44],"as":[11,129],"hate":[12,99],"speech":[13,100],"and":[14,29,32,83,101,135,145,154],"abusive":[15,102],"language":[16,46,88,103,139],"has":[17,59],"become":[18],"increasingly":[19],"widespread":[20],"online.":[21],"This":[22],"type":[23],"can":[26,84],"hurt":[27],"individuals":[28],"create":[30],"negative":[31],"unsafe":[33],"online":[34],"spaces.":[35],"While":[36],"many":[37],"studies":[38],"have":[39,66,126],"been":[40,60,127],"done":[41],"to":[42,62,90,151],"detect":[43],"in":[47,104,122],"widely":[48],"spoken":[49],"languages":[50],"like":[51],"English":[52],"or":[53,131],"Modern":[54,80],"Standard":[55,81],"Arabic,":[56],"less":[57],"attention":[58],"given":[61],"local":[63],"dialects":[64,72],"that":[65,125],"fewer":[67],"resources.":[68],"One":[69],"these":[71],"is":[73,77],"Tunisian":[74,105,123,166],"dialect,":[75,167],"which":[76,118,161],"different":[78,156],"from":[79],"Arabic":[82,153],"be":[85],"harder":[86],"for":[87],"models":[89,148],"understand.":[91],"In":[92],"this":[93],"paper,":[94],"we":[95],"focus":[96],"on":[97,165],"detecting":[98],"dialect":[106,124],"using":[107],"deep":[108],"learning":[109],"methods.":[110],"We":[111,133],"use":[112],"a":[113],"special":[114],"dataset":[115],"called":[116],"T-HSAB,":[117],"contains":[119],"user":[120],"comments":[121],"labeled":[128],"hateful":[130],"abusive.":[132],"train":[134],"test":[136],"several":[137],"BERT-based":[138],"models,":[140],"including":[141],"AraBERT,":[142],"ARBERT,":[143],"MarBERT,":[144],"TunBERT.":[146],"These":[147],"were":[149],"made":[150],"understand":[152],"its":[155],"forms.":[157],"Among":[158],"them,":[159],"TunBERT,":[160],"was":[162],"trained":[163],"specifically":[164],"gives":[168],"best":[170],"results":[171],"when":[172],"identifying":[173],"toxic":[174],"comments.":[175]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-06T00:00:00"}
