[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124659-en":3,"doc-seo-124659-105":30,"detail-sidebar-cat-0-en-105":91},{"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,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},124659,962075006959,"Anda","https://ap-avatar.wpscdn.com/avatar/e0002397efbe92a78e?_k=1776741047341049297",8,"Research & Report","Detecting Suicidality in Arabic Tweets - Using Machine Learning and Deep Learning Techniques","Social media platforms enable rapid, frequent global communication, and users often express negative emotions such as death, self-harm, and hardship, especially among younger generations. Automatic detection of suicidal thoughts in Arabic tweets can support timely intervention, reduce self-harm contagion, and limit the spread of suicidal ideation online. This work creates an Arabic suicidality dataset and evaluates multiple ML and pre-trained deep learning models to identify suicidal content.","arXiv :2309 .00246v 1 [ cs .CL] 1 Sep 2023  \nDetecting Suicidality in Arabic Tweets Using Machine Learning and Deep Learning Techniques  \nAsma Abdulsalam 1*, Areej Alhothali 1 and Saleh Al-Ghamdi2  \n1*Department of Computer Science, Faculty of Computing and Information Technology, King AbdulAziz University, Jeddah, 21589, Saudi Arabia.  \n2Department of Psychology, Faculty of Educational Graduate Studies, King  \nAbdulAziz University, Jeddah, 21589, Saudi Arabia.  \n*Corresponding author(s). E-mail(s): [aabdulsalam0012@stu.kau.edu.sa](aabdulsalam0012@stu.kau.edu.sa) ; Contributing authors: [aalhothali@kau.edu.sa](aalhothali@kau.edu.sa) ; [syalghamdi@kau.edu.sa](syalghamdi@kau.edu.sa) ;  \nAbstract  \nSocial media platforms have revolutionized traditional communication techniques by enabling people globally to connect instantaneously, openly, and frequently. People use social media to share personal stories and express their opinion. Negative emotions such as thoughts of death, self-harm, and hardship are commonly expressed on social media, particularly among younger generations. As a result, using social media to detect suicidal thoughts will help provide proper intervention that will ultimately deter others from selfharm and committing suicide and stop the spread of suicidal ideation on social media. To investigate the ability to detect suicidal thoughts in Arabic tweets automatically, we developed a novel Arabic suicidal tweets dataset, examined several machine learning models, including Naïve Bayes, Support Vector Machine, K-Nearest Neighbor, Random Forest, and XGBoost, trained on word frequency and word embedding features, and investigated the ability of pre-trained deep learning models, AraBert, AraELECTRA, and AraGPT2, to identify suicidal thoughts in Arabic tweets. The results indicate that SVM and RF models trained on character n-gram features provided the best performance in the machine learning models, with 86% accuracy and an F1 score of 79%. The results of the deep learning models show that AraBert model outperforms other machine and deep learning models, achieving an accuracy of 91% and an F1-score of 88%, which significantly improves the detection of suicidal ideation in the Arabic tweets dataset. To the best of our knowledge, this is the first study to develop an Arabic suicidality detection dataset from Twitter and to use deep-learning approaches in detecting suicidality in Arabic posts.  \nKeywords: Suicidality, Suicide ideation, Suicidal thoughts, Natural Language Processing, Twitter, Social Media, Machine Learning, Deep learning, AraBERT, Arabic tweets, Arabic text classification  \n1  \n1 Introduction  \nApproximately 3.96 billion people actively accessed the internet worldwide [1] . Millions of people use social media regularly, such as chat rooms, social networking sites, blogging sites, and social networking platforms. Social media networking sites such as Facebook, Twitter, Snapchat, and other social networking sites allow users to exchange information and interact with others. Twitter is a free social media broadcast site that allows registered users to communicate with others through 280-character messages called \"tweets.\" This popular platform enables users to say or express whatever they want, whether positive or negative. A significant number of users utilize social media networks to convey their feelings, experiences, thoughts, difficulties, and concerns [2] . Self-harming thoughts, death, and suicidal ideation are among the most popular topics discussed on social media. The intended attempt to end the person’s own life is referred to as suicide [3] .  \nSuicide is a phenomenon that arises from a complex interaction of social, biological, cultural, psychological, and spiritual variables [4] . Suicide is a manifestation of underlying suffering that is brought on by a variety of events, such as underlying mental illnesses that create psychological pain [5] . Suicidal behavior includes three types: suicidal be","cbCaiu6R0oHxnCP5","https://ap.wps.com/l/cbCaiu6R0oHxnCP5","pdf",872078,1,22,"English","en",105,"# Introduction\n## Social media and suicide ideation\n## Definitions and impacts of suicide\n## Limits of traditional assessment methods\n## Motivation for automatic detection","[{\"question\":\"Why is automatic detection of suicidality in Arabic tweets important?\",\"answer\":\"Negative emotions related to death and self-harm are commonly expressed on social media. Detecting suicidal thoughts can enable proper intervention and help deter others from self-harm and suicide.\"},{\"question\":\"What dataset and models are used for identifying suicidal thoughts in Arabic tweets?\",\"answer\":\"The study develops an Arabic suicidal tweets dataset and evaluates machine learning models such as Naïve Bayes, SVM, KNN, Random Forest, and XGBoost, plus deep learning models AraBERT, AraELECTRA, and AraGPT2.\"},{\"question\":\"Which approach performs best according to the results?\",\"answer\":\"In machine learning, SVM and RF using character n-gram features achieve about 86% accuracy and an F1 score of 79%. For deep learning, AraBERT achieves about 91% accuracy and an F1 score of 88%, outperforming other models.\"}]","Detecting Suicidality in Arabic Tweets - Using Machine Learning and Deep Learning Techniques | PDF",1785893608,55,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"detecting-suicidality-in-arabic-tweets-using-machine-learning-and-deep-learning-techniques","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/detecting-suicidality-in-arabic-tweets-using-machine-learning-and-deep-learning-techniques/124659/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why is automatic detection of suicidality in Arabic tweets important?","Question",{"text":75,"@type":76},"Negative emotions related to death and self-harm are commonly expressed on social media. Detecting suicidal thoughts can enable proper intervention and help deter others from self-harm and suicide.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What dataset and models are used for identifying suicidal thoughts in Arabic tweets?",{"text":80,"@type":76},"The study develops an Arabic suicidal tweets dataset and evaluates machine learning models such as Naïve Bayes, SVM, KNN, Random Forest, and XGBoost, plus deep learning models AraBERT, AraELECTRA, and AraGPT2.",{"name":82,"@type":73,"acceptedAnswer":83},"Which approach performs best according to the results?",{"text":84,"@type":76},"In machine learning, SVM and RF using character n-gram features achieve about 86% accuracy and an F1 score of 79%. For deep learning, AraBERT achieves about 91% accuracy and an F1 score of 88%, outperforming other models.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]