{"id":"https://openalex.org/W7137142000","doi":"https://doi.org/10.5281/zenodo.19048125","title":"MAGHREB-HOF: A Large-Scale Annotated Corpus for Hate and Offensive Language Detection in Maghrebi Arabic","display_name":"MAGHREB-HOF: A Large-Scale Annotated Corpus for Hate and Offensive Language Detection in Maghrebi Arabic","publication_year":2022,"publication_date":"2022-03-16","ids":{"openalex":"https://openalex.org/W7137142000","doi":"https://doi.org/10.5281/zenodo.19048125"},"language":"arb","primary_location":{"id":"doi:10.5281/zenodo.19048125","doi":"https://doi.org/10.5281/zenodo.19048125","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.19048125","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"volume":null,"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.19048125","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073086303","display_name":"Sadik Bessou","orcid":"https://orcid.org/0000-0001-8891-3688","observed_orcids":["https://orcid.org/0000-0001-8891-3688"]},"institutions":[{"id":"https://openalex.org/I40193446","display_name":"University Ferhat Abbas of Setif","ror":"https://ror.org/02rzqza52","country_code":"DZ","type":"education","lineage":["https://openalex.org/I40193446"]}],"countries":["DZ"],"is_corresponding":false,"raw_author_name":"BESSOU, SADIK","raw_affiliation_strings":["University Ferhat Abbas of Setif"],"raw_orcid":"https://orcid.org/0000-0001-8891-3688","affiliations":[{"raw_affiliation_string":"University Ferhat Abbas of Setif","institution_ids":["https://openalex.org/I40193446"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5120907157","display_name":"Ahmed Zoubir MESSALTI","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I40193446","display_name":"University Ferhat Abbas of Setif","ror":"https://ror.org/02rzqza52","country_code":"DZ","type":"education","lineage":["https://openalex.org/I40193446"]}],"countries":["DZ"],"is_corresponding":false,"raw_author_name":"MESSALTI, Ahmed Zoubir","raw_affiliation_strings":["University Ferhat Abbas of Setif"],"raw_orcid":"https://orcid.org/0000-0002-0047-9301","affiliations":[{"raw_affiliation_string":"University Ferhat Abbas of Setif","institution_ids":["https://openalex.org/I40193446"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I40193446"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":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"}},{"id":"https://openalex.org/T11147","display_name":"Misinformation and Its Impacts","score":0.0,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"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/hate-speech-detection","display_name":"hate speech detection","score":0.8320000171661377},{"id":"https://openalex.org/keywords/offensive-language-identification","display_name":"offensive language detection","score":0.9729999899864197},{"id":"https://openalex.org/keywords/maghrebi-arabic","display_name":"Maghrebi Arabic","score":0.9900000095367432},{"id":"https://openalex.org/keywords/arabic-dialects","display_name":"Arabic dialects","score":0.8220000267028809},{"id":"https://openalex.org/keywords/arabizi","display_name":"Arabizi","score":0.8980000019073486},{"id":"https://openalex.org/keywords/social-media-comments","display_name":"social media comments","score":0.753000020980835},{"id":"https://openalex.org/keywords/annotated-corpora","display_name":"annotated corpus","score":0.9509999752044678},{"id":"https://openalex.org/keywords/annotation-guidelines","display_name":"annotation guidelines","score":0.5860000252723694},{"id":"https://openalex.org/keywords/dialect-identification","display_name":"dialect identification","score":0.6060000061988831},{"id":"https://openalex.org/keywords/arabic-transliteration","display_name":"Arabic transliteration","score":0.3970000147819519}],"concepts":[{"id":"https://openalex.org/C176856949","wikidata":"https://www.wikidata.org/wiki/Q2001676","display_name":"Offensive","level":2,"score":0.800599992275238},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.77920001745224},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6830000281333923},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.6254000067710876},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5674999952316284},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.4975000023841858},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48899999260902405},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.4341999888420105},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.4034000039100647},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36390000581741333},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.3596999943256378},{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.32249999046325684},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2994000017642975},{"id":"https://openalex.org/C2780358164","wikidata":"https://www.wikidata.org/wiki/Q571571","display_name":"Insult","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.2549000084400177},{"id":"https://openalex.org/C119839945","wikidata":"https://www.wikidata.org/wiki/Q6545185","display_name":"Unique identifier","level":3,"score":0.25360000133514404},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.25209999084472656},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.5281/zenodo.19048125","doi":"https://doi.org/10.5281/zenodo.19048125","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.19048125","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},{"id":"doi:10.5281/zenodo.19048126","doi":"https://doi.org/10.5281/zenodo.19048126","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.19048126","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},{"id":"doi:10.5281/zenodo.20597387","doi":"https://doi.org/10.5281/zenodo.20597387","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.20597387","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"doi:10.5281/zenodo.19048125","doi":"https://doi.org/10.5281/zenodo.19048125","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.19048125","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7116301020","https://openalex.org/W7203778822","https://openalex.org/W3087984428","https://openalex.org/W4407059173","https://openalex.org/W4399177229","https://openalex.org/W4379386767","https://openalex.org/W3087096149","https://openalex.org/W3140649021","https://openalex.org/W7213465441","https://openalex.org/W4409403916"],"abstract_inverted_index":{"MAGHREB-HOF:":[0,748],"A":[1,109,173,661,703,749,779,984,1043],"Large-Scale":[2,110,662,704,750,780,985],"Corpus":[3,751,781],"for":[4,19,104,416,656,698,735,752,782,823,853,979,1025,1058],"Hate":[5,106,430,437,658,700,753,783,981],"and":[6,21,37,41,50,70,85,97,101,117,159,204,238,269,292,349,363,381,391,410,418,450,514,542,582,603,639,649,653,669,689,695,713,737,745,754,773,784,811,817,830,840,859,865,894,920,951,973,976,991,1014,1027,1030,1050],"Offensive":[7,755,785],"Language":[8,756,786],"Detection":[9,757,787],"in":[10,26,56,74,131,169,193,233,304,405,444,606,615,618,620,758,788,898],"Maghrebi":[11,27,105,146,368,569,607,657,699,759,789,980,1090],"Arabic":[12,28,570,1100],"MAGHREB-HOF":[13,329,556,912],"is":[14,62,129,258,414,821,907,947,962,1017,1023,1052],"a":[15,621],"large-scale":[16],"annotated":[17,142,415],"corpus":[18,45,143,353,455,807,870],"hate":[20,69,417,561,818,1094],"offensive":[22,71,419,432,564,812,1096],"language":[23,72,565],"(HOF)":[24],"detection":[25,73],"social-media":[29,147,608,863],"text.":[30,609],"The":[31,44,88,127,141,149,164,181,240,352,370,440,512,588,806,869,1021],"dataset":[32,89,241,264,460,589,637,850,897,918,960,1039],"contains":[33,808],"200,000":[34],"anonymized":[35,145,839],"comments":[36,357,396,837],"supports":[38,185],"both":[39,635],"binary":[40,476],"fine-grained":[42,484],"classification.":[43],"includes":[46],"dialectal":[47,76],"Arabic,":[48,760],"Arabizi,":[49],"code-mixed":[51,578],"Arabic\u2013French/English":[52,577],"content":[53,433,586,1111],"commonly":[54],"observed":[55],"North":[57],"African":[58],"online":[59,379,833],"communication.":[60],"It":[61,820],"intended":[63],"to":[64,219,255,321,594,597,875,935,958,1035,1066],"support":[65,558],"reproducible":[66,162],"research":[67,559,631,825],"on":[68,940],"noisy":[75],"environments":[77],"characterized":[78],"by":[79],"spelling":[80,598],"variation,":[81,599],"dialect":[82,540,552],"mixing,":[83],"transliteration,":[84,602],"informal":[86,600],"writing.":[87],"accompanies":[90],"the":[91,154,170,177,188,194,221,230,234,246,256,263,267,274,277,295,301,305,322,367,406,448,509,520,636,640,849,896,901,921,936,941,949,959,965,1047,1059],"peer-reviewed":[92,642,923],"article:":[93],"Ahmed":[94,646,687,742,771,970,1073],"Zoubir":[95,647,688,743,772,971,1074],"Messalti":[96,648,744,972],"Sadik":[98,650,746,974],"Bessou,":[99,651,690,747,774],"\u201cWord":[100,652],"Character":[102,654,696,977],"Models":[103,655,697,978],"Speech":[107,659,701,982],"Detection:":[108,660,702,983],"Facebook":[111,361,663,705,986],"Corpus,\u201d":[112,664],"International":[113,665,887],"Journal":[114,666,710,988],"of":[115,144,187,249,667,711,989,1077,1081],"Computers":[116,668,712,736,990],"their":[118,670,714,992],"Applications,":[119,671,993],"vol.":[120,672,994],"33,":[121,673,995],"no.":[122,674,996],"3,":[123,675,997],"pp.":[124,676,998],"255\u2013266,":[125,677,999],"2026.":[126,678,762,1000],"article":[128],"indexed":[130],"Scopus.":[132],"What":[133],"This":[134,137],"Record":[135],"Contains":[136],"Zenodo":[138,251,917,932],"record":[139,252,446,638,933,942],"provides:":[140],"comments.":[148],"annotation":[150,270,441,1048],"guidelines":[151,271,442],"used":[152,168,453,593,874],"during":[153,454],"labeling":[155],"process.":[156],"Label":[157],"definitions":[158,449],"metadata":[160,501,950,1012],"supporting":[161],"experimentation.":[163],"official":[165,178],"split-index":[166,297],"file":[167,175,298],"experiments":[171,302],"(.xlsx).":[172],"README":[174,268],"describing":[176],"experimental":[179,190],"partitions.":[180],"provided":[182,222,296,904,1024,1064],"partition":[183],"information":[184],"reproduction":[186],"two":[189],"tracks":[191],"reported":[192,232,303],"companion":[195,235,306,641,922],"paper:":[196],"Sparse":[197],"linear":[198],"models:":[199,211],"stratified":[200,212],"70/30":[201],"holdout":[202],"split":[203],"five-fold":[205],"cross-validation":[206],"where":[207,344],"applicable.":[208],"Neural":[209],"sequence":[210],"70/15/15":[213],"train/validation/test":[214,338],"split.":[215],"Researchers":[216,847],"are":[217,397,402,528,536,838,928],"encouraged":[218],"use":[220,613],"partitions":[223],"when":[224,253,299,1070],"directly":[225],"comparing":[226],"new":[227],"models":[228],"with":[229,366,508,855,900],"results":[231],"article.":[236,307,643,924],"Download":[237],"Use":[239,294,555],"can":[242,557],"be":[243,546,592,873,1063],"downloaded":[244],"from":[245,356,359],"Files":[247],"section":[248],"this":[250,445,916,931],"access":[254,937,957,1034],"files":[257,927,961],"available.":[259],"After":[260],"downloading:":[261],"Extract":[262],"files.":[265,1040],"Consult":[266],"before":[272],"preprocessing":[273,312,336],"corpus.":[275],"Select":[276],"required":[278],"task":[279,334],"formulation:":[280],"Binary":[281,421],"classification:":[282,288],"Clean":[283,425,436],"vs.":[284],"Hate/Offensive":[285],"Language.":[286],"Fine-grained":[287],"Clean,":[289],"Hate,":[290,487],"Insult,":[291,488],"Profanity.":[293],"reproducing":[300],"Clearly":[308],"document":[309],"any":[310],"alternative":[311],"procedure,":[313],"data":[314,864],"partition,":[315],"label":[316,474,478,485,1010],"transformation,":[317],"or":[318,431,489,551,617,629,878,1037,1068],"filtering":[319],"applied":[320],"original":[323,471],"dataset.":[324,408],"For":[325],"reproducibility,":[326],"publications":[327],"using":[328,519,848,911],"should":[330,543,871,913],"report":[331],"at":[332,827],"least:":[333],"formulation;":[335],"procedure;":[337],"partition;":[339],"model":[340,511],"configuration;":[341],"random":[342],"seed":[343],"applicable;":[345],"evaluation":[346],"metrics.":[347],"Source":[348],"Data":[350],"Collection":[351],"was":[354],"constructed":[355],"collected":[358,371],"public":[360],"pages":[362,725],"posts":[364],"associated":[365,507],"region.":[369],"discussions":[372],"cover":[373],"topics":[374],"that":[375],"may":[376,590,892,1062],"generate":[377],"substantial":[378],"interaction":[380],"potentially":[382,809,866],"hostile":[383],"exchanges,":[384],"including":[385,814],"politics,":[386],"identity-related":[387],"issues,":[388],"social":[389,1102],"topics,":[390],"sports":[392],"rivalries.":[393],"All":[394,835],"released":[395,822],"anonymized.":[398],"Direct":[399],"personal":[400,842],"identifiers":[401,843],"not":[403,537,545,872,1032],"included":[404,443,529],"distributed":[407,836,929],"Annotation":[409,1041],"Labels":[411],"Each":[412],"comment":[413,467,472],"language.":[420],"Classification":[422,435],"0":[423],"\u2014":[424,429,464,470,475,483,498,503,680,765],"/":[426,480],"non-offensive":[427],"1":[428,1085],"Fine-Grained":[434],"Insult":[438],"Profanity":[439],"provide":[447,1033],"decision":[451],"rules":[452],"construction.":[456],"Core":[457],"Columns":[458],"Typical":[459],"fields":[461,516],"include:":[462],"ID":[463],"unique":[465],"internal":[466],"identifier":[468],"Comments_origine":[469],"text":[473,573,584,1109],"HOF":[477],"(0":[479],"1)":[481],"label_multi":[482],"(Clean,":[486],"Profanity)":[490],"Comments_Date":[491],"Annotation_Date":[492],"Page":[493],"Post":[494],"Hub":[495],"Post_Date":[496],"City":[497,513],"predicted":[499],"dialect/city":[500],"Score":[502,515],"prediction":[504],"confidence":[505],"score":[506],"dialect-identification":[510],"were":[517],"generated":[518,532],"pretrained":[521],"Hugging":[522],"Face":[523],"model:":[524],"https://huggingface.co/Ammar-alhaj-ali/arabic-MARBERT-dialect-identification-city":[525],"These":[526],"predictions":[527],"as":[530,548],"automatically":[531],"descriptive":[533,1008],"metadata.":[534],"They":[535],"manually":[538],"validated":[539],"annotations":[541],"therefore":[544],"treated":[547],"gold-standard":[549],"geographic":[550],"labels.":[553],"Recommended":[554],"on:":[560],"speech":[562],"detection;":[563,566,568,1099],"toxicity":[567,1098],"NLP;":[571,579,1101],"dialect-robust":[572],"classification;":[574,1110],"Arabizi":[575],"processing;":[576],"character-,":[580],"word-,":[581],"subword-level":[583],"representation;":[585],"moderation.":[587],"also":[591],"evaluate":[595],"robustness":[596],"writing,":[601],"lexical":[604],"variation":[605],"Citation":[610],"If":[611,944],"you":[612],"MAGHREB-HOF,":[614],"whole":[616],"part,":[619],"scientific":[622,824],"publication,":[623],"thesis,":[624],"dissertation,":[625],"software":[626],"project,":[627],"benchmark,":[628],"other":[630],"output,":[632],"please":[633],"cite":[634,914],"Companion":[644,681],"Article":[645,682],"BibTeX":[679,764],"@article{Messalti2026WordCharacter,":[683],"author":[684,768],"=":[685,693,708,717,720,723,726,729,732,769,777,792,795,798,801],"{Messalti,":[686,770],"Sadik},":[691,775],"title":[692,776],"{Word":[694],"Corpus},":[706],"journal":[707],"{International":[709,733],"Applications},":[715],"year":[716,791],"{2026},":[718,793],"volume":[719],"{33},":[721],"number":[722],"{3},":[724],"{255--266},":[727],"issn":[728],"{1076-5204},":[730],"publisher":[731,794],"Society":[734],"Their":[738],"Applications}":[739],"}":[740,803],"Dataset":[741,766,926,1001],"Zenodo,":[761],"https://doi.org/10.5281/zenodo.19048125":[763],"@dataset{Messalti2026MAGHREBHOF,":[767],"{MAGHREB-HOF:":[778],"Arabic},":[790],"{Zenodo},":[796],"doi":[797],"{10.5281/zenodo.19048125},":[799],"url":[800],"{https://doi.org/10.5281/zenodo.19048125}":[802],"Ethical":[804],"Considerations":[805],"harmful":[810,832,867],"language,":[813],"insults,":[815],"profanity,":[816],"speech.":[819],"aimed":[826],"understanding,":[828],"detecting,":[829],"mitigating":[831],"content.":[834,868],"direct":[841],"have":[844],"been":[845],"removed.":[846],"remain":[851,953],"responsible":[852],"complying":[854],"applicable":[856],"institutional,":[857],"legal,":[858],"ethical":[860],"requirements":[861],"concerning":[862],"identify,":[876],"profile,":[877],"target":[879],"individual":[880],"users.":[881],"License":[882],"Creative":[883],"Commons":[884],"Attribution":[885],"4.0":[886],"(CC":[888],"BY":[889],"4.0).":[890],"Users":[891],"reuse":[893],"adapt":[895],"accordance":[899],"license":[902],"conditions,":[903],"appropriate":[905],"attribution":[906],"given.":[908],"Scientific":[909],"works":[910],"both:":[915],"record;":[919],"Access":[925,1056],"through":[930],"according":[934],"conditions":[938],"indicated":[939],"page.":[943],"an":[945],"embargo":[946,966],"active,":[948],"DOI":[952],"publicly":[954],"visible":[955],"while":[956],"restricted":[963,1036],"until":[964],"expires.":[967],"Related":[968],"Publication":[969],"Bessou\u201cWord":[975],"Corpus.\u201dInternational":[987],"Statistics":[1002],"Dashboard":[1003],"An":[1004],"interactive":[1005],"dashboard":[1006,1022],"providing":[1007],"statistics,":[1009],"distributions,":[1011],"summaries,":[1013],"exploratory":[1015],"views":[1016],"available":[1018,1053],"at:":[1019,1054],"http://magh-arabic-hof.duckdns.org:3000/public/dashboard/4a359fc9-bfe5-498b-93f6-957335e5ccf1/page":[1020],"exploration":[1026],"reporting":[1028],"purposes":[1029],"does":[1031],"embargoed":[1038],"Demo":[1042],"Doccano":[1044],"instance":[1045],"demonstrating":[1046],"interface":[1049],"workflow":[1051],"http://magh-arabic-hof.duckdns.org:8800/auth":[1055],"credentials":[1057],"demonstration":[1060],"environment":[1061],"privately":[1065],"reviewers":[1067],"researchers":[1069],"appropriate.":[1071],"Contact":[1072],"MessaltiLRSD":[1075],"LaboratoryDepartment":[1076],"Computer":[1078],"Science,":[1079],"Faculty":[1080],"SciencesFerhat":[1082],"Abbas":[1083],"S\u00e9tif":[1084],"UniversityAlgeria":[1086],"Email:":[1087],"ahmedzoubir.messalti@univ-setif.dz":[1088],"Keywords":[1089],"Arabic;":[1091],"Arabizi;":[1092],"code-mixing;":[1093],"speech;":[1095],"language;":[1097],"media":[1103],"corpus;":[1104],"machine":[1105],"learning;":[1106,1108],"deep":[1107],"moderation":[1112]},"counts_by_year":[],"updated_date":"2026-10-08T09:06:37.294493","created_date":"2026-03-17T00:00:00"}
