{"id":"https://openalex.org/W4413699094","doi":"https://doi.org/10.21203/rs.3.rs-7402208/v1","title":"BERT-Based Model for Identifying Hate Speech and Offensive Language in Arabic Social Media","display_name":"BERT-Based Model for Identifying Hate Speech and Offensive Language in Arabic Social Media","publication_year":2025,"publication_date":"2025-08-26","ids":{"openalex":"https://openalex.org/W4413699094","doi":"https://doi.org/10.21203/rs.3.rs-7402208/v1"},"language":"en","primary_location":{"id":"doi:10.21203/rs.3.rs-7402208/v1","doi":"https://doi.org/10.21203/rs.3.rs-7402208/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-7402208/v1","pdf_url":"https://www.researchsquare.com/article/rs-7402208/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Research Square","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.researchsquare.com/article/rs-7402208/latest.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088380487","display_name":"Aiman M. Ayyal Awwad","orcid":"https://orcid.org/0000-0002-1378-8381","observed_orcids":["https://orcid.org/0000-0002-1378-8381"]},"institutions":[{"id":"https://openalex.org/I114432678","display_name":"Tafila Technical University","ror":"https://ror.org/04jzmk773","country_code":"JO","type":"education","lineage":["https://openalex.org/I114432678"]}],"countries":["JO"],"is_corresponding":true,"raw_author_name":"Aiman M. Ayyal Awwad","raw_affiliation_strings":["Tafila Technical University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tafila Technical University","institution_ids":["https://openalex.org/I114432678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066806787","display_name":"Farhan Alebeisat","orcid":"https://orcid.org/0000-0002-9108-4881","observed_orcids":["https://orcid.org/0000-0002-9108-4881"]},"institutions":[{"id":"https://openalex.org/I145019703","display_name":"Al-Zaytoonah University of Jordan","ror":"https://ror.org/04a5b0p13","country_code":"JO","type":"education","lineage":["https://openalex.org/I145019703"]}],"countries":["JO"],"is_corresponding":false,"raw_author_name":"Farhan Alebeisat","raw_affiliation_strings":["Al-Zaytoonah University of Jordan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Al-Zaytoonah University of Jordan","institution_ids":["https://openalex.org/I145019703"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5119440692","display_name":"Ra\u2019dah A. Alsmeheen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I33926330","display_name":"Al-Balqa Applied University","ror":"https://ror.org/00qedmt22","country_code":"JO","type":"education","lineage":["https://openalex.org/I33926330"]}],"countries":["JO"],"is_corresponding":false,"raw_author_name":"Ra\u2019dah A. Alsmeheen","raw_affiliation_strings":["Al-Balqa\u2018 Applied University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Al-Balqa\u2018 Applied University","institution_ids":["https://openalex.org/I33926330"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5088380487"],"corresponding_institution_ids":["https://openalex.org/I114432678"],"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":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/T10028","display_name":"Topic Modeling","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"}}],"keywords":[{"id":"https://openalex.org/keywords/hate-speech-detection","display_name":"hate speech detection","score":0.9980000257492065},{"id":"https://openalex.org/keywords/offensive-language-identification","display_name":"offensive language detection","score":0.8339999914169312},{"id":"https://openalex.org/keywords/arabic-text","display_name":"Arabic text","score":0.6169999837875366},{"id":"https://openalex.org/keywords/bert","display_name":"BERT","score":0.7839999794960022},{"id":"https://openalex.org/keywords/marbert","display_name":"MARBERT","score":0.7559999823570251},{"id":"https://openalex.org/keywords/arabert","display_name":"AraBERT","score":0.996999979019165},{"id":"https://openalex.org/keywords/twitter","display_name":"Twitter","score":0.6039999723434448},{"id":"https://openalex.org/keywords/small-datasets","display_name":"small datasets","score":0.5289999842643738},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"support vector machine","score":0.7730000019073486},{"id":"https://openalex.org/keywords/random-forest","display_name":"random forest","score":0.8159999847412109},{"id":"https://openalex.org/keywords/principal-component-analysis","display_name":"principal component analysis","score":0.7070000171661377},{"id":"https://openalex.org/keywords/arabic-social-media","display_name":"Arabic social media","score":0.7239999771118164}],"concepts":[{"id":"https://openalex.org/C176856949","wikidata":"https://www.wikidata.org/wiki/Q2001676","display_name":"Offensive","level":2,"score":0.9587860107421875},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.8059737682342529},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5751066207885742},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.45393502712249756},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42779237031936646},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.42304667830467224},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11018803715705872},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.09800699353218079},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.07180693745613098},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.06260627508163452}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21203/rs.3.rs-7402208/v1","doi":"https://doi.org/10.21203/rs.3.rs-7402208/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-7402208/v1","pdf_url":"https://www.researchsquare.com/article/rs-7402208/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Research Square","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.21203/rs.3.rs-7402208/v1","doi":"https://doi.org/10.21203/rs.3.rs-7402208/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-7402208/v1","pdf_url":"https://www.researchsquare.com/article/rs-7402208/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Research Square","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4413699094.pdf","grobid_xml":"https://content.openalex.org/works/W4413699094.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W1984708705","https://openalex.org/W2118023920","https://openalex.org/W2172238468","https://openalex.org/W2753648062","https://openalex.org/W2770568736","https://openalex.org/W2772752821","https://openalex.org/W2901236145","https://openalex.org/W2912213068","https://openalex.org/W2922580172","https://openalex.org/W3010327946","https://openalex.org/W3023211159","https://openalex.org/W3025255083","https://openalex.org/W3033561598","https://openalex.org/W3087096149","https://openalex.org/W3106580412","https://openalex.org/W3110474128","https://openalex.org/W3115903740","https://openalex.org/W3126087996","https://openalex.org/W3126181281","https://openalex.org/W3139580003","https://openalex.org/W3155468913","https://openalex.org/W3163832451","https://openalex.org/W3165722314","https://openalex.org/W3172559340","https://openalex.org/W3192799006","https://openalex.org/W3194343069","https://openalex.org/W3210610489","https://openalex.org/W4205995027","https://openalex.org/W4238481634","https://openalex.org/W4285272262","https://openalex.org/W4289258965","https://openalex.org/W4317212783","https://openalex.org/W4321373414","https://openalex.org/W4361214844","https://openalex.org/W4382301295","https://openalex.org/W4391970070","https://openalex.org/W4392728800","https://openalex.org/W4400134761","https://openalex.org/W4404758309"],"related_works":["https://openalex.org/W4321373414","https://openalex.org/W4416444941","https://openalex.org/W4412533364","https://openalex.org/W4391970070","https://openalex.org/W4401703256","https://openalex.org/W4385883875","https://openalex.org/W3106580412","https://openalex.org/W4385454654","https://openalex.org/W4285272262","https://openalex.org/W4312736021"],"abstract_inverted_index":{"Abstract":[0],"Nowadays,":[1],"addressing":[2],"hate":[3,83,117],"speech":[4,84,118],"has":[5],"become":[6],"a":[7],"major":[8],"social":[9,31],"and":[10,60,85,116,128,156,166,196,233,243,249],"political":[11],"concern":[12],"due":[13,53,103],"to":[14,21,54,81,104,123,153,172],"its":[15],"harmful":[16],"impact.":[17],"It":[18],"is":[19,36],"essential":[20],"develop":[22],"detection":[23],"techniques,":[24],"given":[25],"the":[26,55,58,61,70,73,99,105,111,125,131,140,143,163,174,220,224,253,257],"evolving":[27],"expression":[28],"patterns":[29],"on":[30,37,203,223,256],"media":[32],"platforms.":[33],"The":[34,120,206,235],"focus":[35],"natural":[38],"language":[39,59],"processing,":[40],"which":[41,109],"analyzes":[42],"complex":[43],"texts":[44],"effectively.":[45],"Arabic":[46],"Natural":[47],"Language":[48],"Processing":[49],"presents":[50],"significant":[51],"challenges":[52,112],"complexity":[56],"of":[57,64,72,113,130,142,162],"limited":[62],"availability":[63],"high-quality":[65],"data.":[66],"This":[67],"paper":[68],"investigates":[69],"use":[71],"Bidirectional":[74],"Encoder":[75],"Representation":[76],"from":[77],"Transformers":[78],"(BERT)":[79],"model":[80,133,165,222,255],"detect":[82],"classify":[86],"data":[87,101],"using":[88,252],"machine":[89],"learning":[90],"(ML)":[91],"algorithms.":[92,146],"Platform":[93],"X":[94],"(Twitter)":[95],"was":[96,151],"chosen":[97],"as":[98],"primary":[100],"source":[102],"short":[106],"text":[107,114],"format":[108],"highlights":[110],"processing":[115],"detection.":[119],"study":[121],"seeks":[122],"assess":[124],"performance,":[126],"robustness,":[127],"stability":[129],"BERT":[132,164,192],"across":[134,186],"different":[135,187],"dataset":[136,168,188],"sizes,":[137,189],"along":[138,227],"with":[139,198,219,228],"effectiveness":[141],"selected":[144],"ML":[145],"Principal":[147],"Component":[148],"Analysis":[149],"(PCA)":[150],"applied":[152],"reduce":[154],"dimensionality":[155],"yielded":[157,239],"positive":[158],"results.":[159],"Three":[160],"versions":[161],"three":[167],"sizes":[169],"were":[170],"used":[171],"achieve":[173],"study\u2019s":[175],"objectives.":[176],"Experimental":[177],"results":[178],"showed":[179],"that":[180,191],"classification":[181],"performance":[182,200],"remained":[183],"relatively":[184],"stable":[185],"indicating":[190],"models":[193,266],"are":[194],"robust":[195],"scalable,":[197],"minimal":[199],"degradation":[201],"even":[202],"small":[204,225,258],"datasets.":[205],"Support":[207,261],"Vector":[208,262],"Machine":[209,263],"algorithm":[210,238],"performed":[211],"best":[212],"in":[213],"most":[214],"scenarios,":[215],"reaching":[216],"82%":[217],"accuracy":[218],"MARBERT":[221],"dataset,":[226],"81%":[229],"for":[230,245],"F1,":[231,247],"Precision,":[232,248],"Recall.":[234],"Random":[236],"Forests":[237],"81%,":[240],"79%,":[241],"82%,":[242],"78%":[244],"accuracy,":[246],"Recall,":[250],"respectively,":[251],"ARABERT":[254],"dataset.":[259],"However,":[260],"outperformed":[264],"other":[265],"overall.":[267]},"counts_by_year":[],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2025-10-10T00:00:00"}