[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-31766":3,"doc-seo-31766":27},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"file_id":15,"file_url":16,"file_type":17,"file_size":18,"view_count":4,"is_deleted":4,"is_public":19,"is_downloadable":19,"audit_status":19,"page_count":20,"language":21,"language_code":22,"table_of_contents":23,"faqs":24,"seo_title":13,"seo_description":14,"update_tm":25,"read_time":26},31766,2336464648322,"Aria","https://ap-avatar.wpscdn.com/avatar/2200025388227c56fec?_k=1778556882303663488",8,"Research & Report","Leveraging Advanced Deep Learning Approaches for Detecting Implicit Hate Speech in Arabic","Implicit hate speech is subtle and nuanced, making automated detection difficult due to sarcasm, coded language, and implied meanings that depend heavily on cultural and linguistic context. The study addresses an overlooked gap for Arabic by proposing an Arabic-focused detection framework and introducing an implicit hate speech dataset of about 2,500 records compiled from existing hate-speech datasets. It develops and evaluates ML, deep learning, and transformer-based and hybrid models, finding hybrid transformer approaches achieve the highest accuracies.","cbCainmoJOH1waf8","https://ap.wps.com/l/cbCainmoJOH1waf8","pdf",1768612,1,21,"English","en","# Abstract\n# Keywords\n# Introduction","[{\"question\":\"What makes implicit hate speech harder to detect than explicit hate speech?\",\"answer\":\"Implicit hate speech uses subtle, indirect references and ambiguous contexts, often relying on sarcasm and coded language. Its meaning depends strongly on cultural and linguistic context, which complicates automated identification.\"},{\"question\":\"What dataset is introduced for Arabic implicit hate speech detection?\",\"answer\":\"The study presents a novel Arabic implicit hate speech dataset of approximately 2,500 records. The dataset is collected from multiple hate speech datasets.\"},{\"question\":\"Which model approaches performed best in the experiments?\",\"answer\":\"Hybrid models showed notably strong results. A hybrid combining BiLSTM, CNN, and GRU reached 82% accuracy, while a hybrid combining MarBERT and Qarib reached 86%. MarBERT alone achieved 87%, and GRU with FastText reached 83%.\"}]",1780088536,53,{"code":4,"msg":28,"data":29},"ok",{"site_id":30,"language":22,"slug":31,"title":13,"keywords":32,"description":14,"schema_data":33,"social_meta":84,"head_meta":86,"extra_data":88,"updated_unix":25},105,"leveraging-advanced-deep-learning-approaches-for-detecting-implicit-hate-speech-in-arabic","",{"@graph":34,"@context":83},[35,52,66],{"@type":36,"itemListElement":37},"BreadcrumbList",[38,42,46,49],{"item":39,"name":40,"@type":41,"position":19},"https://docshare.wps.com","Home","ListItem",{"item":43,"name":44,"@type":41,"position":45},"https://docshare.wps.com/document/","Document",2,{"item":47,"name":12,"@type":41,"position":48},"https://docshare.wps.com/document/research-report/",3,{"item":50,"name":13,"@type":41,"position":51},"https://docshare.wps.com/document/leveraging-advanced-deep-learning-approaches-for-detecting-implicit-hate-speech-in-arabic/31766/",4,{"url":50,"name":13,"@type":53,"author":54,"headline":13,"publisher":56,"fileFormat":59,"description":14,"dateModified":60,"datePublished":60,"encodingFormat":59,"isAccessibleForFree":61,"interactionStatistic":62},"DigitalDocument",{"name":9,"@type":55},"Person",{"url":39,"name":57,"@type":58},"DocShare","Organization","application/pdf","2026-05-29",true,{"@type":63,"interactionType":64,"userInteractionCount":4},"InteractionCounter",{"@type":65},"ViewAction",{"@type":67,"mainEntity":68},"FAQPage",[69,75,79],{"name":70,"@type":71,"acceptedAnswer":72},"What makes implicit hate speech harder to detect than explicit hate speech?","Question",{"text":73,"@type":74},"Implicit hate speech uses subtle, indirect references and ambiguous contexts, often relying on sarcasm and coded language. Its meaning depends strongly on cultural and linguistic context, which complicates automated identification.","Answer",{"name":76,"@type":71,"acceptedAnswer":77},"What dataset is introduced for Arabic implicit hate speech detection?",{"text":78,"@type":74},"The study presents a novel Arabic implicit hate speech dataset of approximately 2,500 records. The dataset is collected from multiple hate speech datasets.",{"name":80,"@type":71,"acceptedAnswer":81},"Which model approaches performed best in the experiments?",{"text":82,"@type":74},"Hybrid models showed notably strong results. A hybrid combining BiLSTM, CNN, and GRU reached 82% accuracy, while a hybrid combining MarBERT and Qarib reached 86%. MarBERT alone achieved 87%, and GRU with FastText reached 83%.","https://schema.org",{"og:url":50,"og:type":85,"og:title":13,"og:site_name":57,"og:description":14},"article",{"robots":87,"canonical":50},"index,follow",{"doc_id":7,"site_id":30}]