{"id":"https://openalex.org/W4399177229","doi":"https://doi.org/10.3389/frai.2024.1391472","title":"Hate speech detection with ADHAR: a multi-dialectal hate speech corpus in Arabic","display_name":"Hate speech detection with ADHAR: a multi-dialectal hate speech corpus in Arabic","publication_year":2024,"publication_date":"2024-05-30","ids":{"openalex":"https://openalex.org/W4399177229","doi":"https://doi.org/10.3389/frai.2024.1391472","pmid":"https://pubmed.ncbi.nlm.nih.gov/38873176"},"language":"en","primary_location":{"id":"doi:10.3389/frai.2024.1391472","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frai.2024.1391472","pdf_url":"https://www.frontiersin.org/articles/10.3389/frai.2024.1391472/pdf?isPublishedV2=False","source":{"id":"https://openalex.org/S4210197006","display_name":"Frontiers in Artificial Intelligence","issn_l":"2624-8212","issn":["2624-8212"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.frontiersin.org/articles/10.3389/frai.2024.1391472/pdf?isPublishedV2=False","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029753508","display_name":"Anis Charfi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089979","display_name":"Carnegie Mellon University Qatar","ror":"https://ror.org/00az5dt38","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210089979","https://openalex.org/I74973139"]}],"countries":["QA"],"is_corresponding":true,"raw_author_name":"Anis Charfi","raw_affiliation_strings":["Information Systems Department, Carnegie Mellon University, Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"Information Systems Department, Carnegie Mellon University, Doha, Qatar","institution_ids":["https://openalex.org/I4210089979"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5098946788","display_name":"Mabrouka Besghaier","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089979","display_name":"Carnegie Mellon University Qatar","ror":"https://ror.org/00az5dt38","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210089979","https://openalex.org/I74973139"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Mabrouka Besghaier","raw_affiliation_strings":["Information Systems Department, Carnegie Mellon University, Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"Information Systems Department, Carnegie Mellon University, Doha, Qatar","institution_ids":["https://openalex.org/I4210089979"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5098946789","display_name":"Raghda Akasheh","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089979","display_name":"Carnegie Mellon University Qatar","ror":"https://ror.org/00az5dt38","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210089979","https://openalex.org/I74973139"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Raghda Akasheh","raw_affiliation_strings":["Information Systems Department, Carnegie Mellon University, Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"Information Systems Department, Carnegie Mellon University, Doha, Qatar","institution_ids":["https://openalex.org/I4210089979"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5098946790","display_name":"Andria Atalla","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089979","display_name":"Carnegie Mellon University Qatar","ror":"https://ror.org/00az5dt38","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210089979","https://openalex.org/I74973139"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Andria Atalla","raw_affiliation_strings":["Information Systems Department, Carnegie Mellon University, Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"Information Systems Department, Carnegie Mellon University, Doha, Qatar","institution_ids":["https://openalex.org/I4210089979"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047390057","display_name":"Wajdi Zaghouani","orcid":"https://orcid.org/0000-0003-1521-5568"},"institutions":[{"id":"https://openalex.org/I4210144839","display_name":"Hamad bin Khalifa University","ror":"https://ror.org/03eyq4y97","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210144839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Wajdi Zaghouani","raw_affiliation_strings":["College of Humanities and Social Sciences, Hamad Bin Khalifa University, Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"College of Humanities and Social Sciences, Hamad Bin Khalifa University, Doha, Qatar","institution_ids":["https://openalex.org/I4210144839"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5029753508"],"corresponding_institution_ids":["https://openalex.org/I4210089979"],"apc_list":{"value":1150,"currency":"USD","value_usd":1150},"apc_paid":{"value":1150,"currency":"USD","value_usd":1150},"fwci":4.8872,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.95582728,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"7","issue":null,"first_page":"1391472","last_page":"1391472"},"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/T13959","display_name":"Swearing, Euphemism, Multilingualism","score":0.9047999978065491,"subfield":{"id":"https://openalex.org/subfields/3315","display_name":"Communication"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.7582101821899414},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5416032075881958},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48035773634910583},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4630890190601349},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33566147089004517},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.31696030497550964},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.1946152150630951},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.048687130212783813}],"concepts":[{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.7582101821899414},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5416032075881958},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48035773634910583},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4630890190601349},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33566147089004517},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.31696030497550964},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.1946152150630951},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.048687130212783813}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.3389/frai.2024.1391472","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frai.2024.1391472","pdf_url":"https://www.frontiersin.org/articles/10.3389/frai.2024.1391472/pdf?isPublishedV2=False","source":{"id":"https://openalex.org/S4210197006","display_name":"Frontiers in Artificial Intelligence","issn_l":"2624-8212","issn":["2624-8212"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence","raw_type":"journal-article"},{"id":"pmid:38873176","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38873176","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in artificial intelligence","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:11170444","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11170444","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11170444/pdf/frai-07-1391472.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Front Artif Intell","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:aa1fdaf017ed45698f91ceae3e9f86d1","is_oa":true,"landing_page_url":"https://doaj.org/article/aa1fdaf017ed45698f91ceae3e9f86d1","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Frontiers in Artificial Intelligence, Vol 7 (2024)","raw_type":"article"},{"id":"pmh:oai:figshare.com:article/26355037","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/Hate_speech_detection_with_ADHAR_a_multi-dialectal_hate_speech_corpus_in_Arabic/26355037","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3389/frai.2024.1391472","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frai.2024.1391472","pdf_url":"https://www.frontiersin.org/articles/10.3389/frai.2024.1391472/pdf?isPublishedV2=False","source":{"id":"https://openalex.org/S4210197006","display_name":"Frontiers in Artificial Intelligence","issn_l":"2624-8212","issn":["2624-8212"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.699999988079071}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332753","display_name":"Qatar National Research Fund","ror":"https://ror.org/01svaqq28"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399177229.pdf"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W2898401058","https://openalex.org/W2971150411","https://openalex.org/W2972463128","https://openalex.org/W3003499884","https://openalex.org/W3014064185","https://openalex.org/W3036385388","https://openalex.org/W3093198074","https://openalex.org/W3096800297","https://openalex.org/W3126181281","https://openalex.org/W3163723685","https://openalex.org/W3185909895","https://openalex.org/W3210610489","https://openalex.org/W4313531555","https://openalex.org/W4321373414","https://openalex.org/W4366087566","https://openalex.org/W4385723172","https://openalex.org/W6768444924","https://openalex.org/W6773255457","https://openalex.org/W6784243489"],"related_works":["https://openalex.org/W191108438","https://openalex.org/W3135230428","https://openalex.org/W2904739811","https://openalex.org/W249088392","https://openalex.org/W2152158029","https://openalex.org/W2012540220","https://openalex.org/W2131711534","https://openalex.org/W2559837139","https://openalex.org/W1151175420","https://openalex.org/W2407342067"],"abstract_inverted_index":{"Hate":[0],"speech":[1,21,32,58,85,164,178,201],"detection":[2,179],"in":[3],"Arabic":[4,24,73],"poses":[5],"a":[6,124],"complex":[7],"challenge":[8],"due":[9],"to":[10,101,110,174,182],"the":[11,15,117,139,159,208],"dialectal":[12],"diversity":[13],"across":[14,38,104],"Arab":[16],"world.":[17],"Most":[18],"existing":[19],"hate":[20,31,57,84,163,177,200],"datasets":[22],"for":[23,60,166,176,184,199,207],"cover":[25],"only":[26],"one":[27,30],"dialect":[28],"or":[29],"category.":[33],"They":[34],"also":[35],"lack":[36],"balance":[37,103],"dialects,":[39,105],"topics,":[40],"and":[41,66,78,90,107,135,141,150,170,180,195],"hate/non-hate":[42,108],"classes.":[43],"In":[44],"this":[45,49],"paper,":[46],"we":[47,191],"address":[48],"gap":[50],"by":[51,123],"presenting":[52],"ADHAR-a":[53],"comprehensive":[54],"multi-dialect,":[55],"multi-category":[56],"corpus":[59],"Arabic.":[61],"ADHAR":[62,97],"contains":[63],"70,369":[64],"words":[65],"spans":[67],"four":[68,82],"language":[69],"variants:":[70],"Modern":[71],"Standard":[72],"(MSA),":[74],"Egyptian,":[75],"Levantine,":[76],"Gulf":[77],"Maghrebi.":[79],"It":[80],"covers":[81],"key":[83],"categories:":[86],"nationality,":[87],"religion,":[88],"ethnicity,":[89],"race.":[91],"A":[92],"major":[93],"contribution":[94],"is":[95,98],"that":[96,155],"carefully":[99],"curated":[100],"maintain":[102],"categories,":[106],"classes":[109],"enable":[111],"unbiased":[112],"dataset":[113,157],"evaluation.":[114],"We":[115],"describe":[116],"systematic":[118],"data":[119],"collection":[120],"methodology,":[121],"followed":[122],"rigorous":[125],"annotation":[126],"process":[127],"involving":[128],"multiple":[129],"annotators":[130],"per":[131],"dialect.":[132],"Extensive":[133],"qualitative":[134],"quantitative":[136],"analyses":[137],"demonstrate":[138,154],"quality":[140],"usefulness":[142],"of":[143,161,172,197],"ADHAR.":[144],"Our":[145],"experiments":[146],"with":[147,189],"various":[148],"classical":[149],"deep":[151],"learning":[152],"models":[153],"our":[156],"enables":[158],"development":[160],"robust":[162],"classifiers":[165],"Arabic,":[167],"achieving":[168],"accuracy":[169,194],"F1-scores":[171],"up":[173,181],"90%":[175],"92%":[183],"category":[185,209],"detection.":[186,210],"When":[187],"trained":[188],"Arabert,":[190],"achieved":[192],"an":[193],"F1-score":[196],"94%":[198],"detection,":[202],"as":[203,205],"well":[204],"95%":[206]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":6}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}