An optimized deep learning approach for suicide detection through Arabic tweets

Nadiah A Baghdadi; Amer Malki; Hossam Magdy Balaha; Yousry AbdulAzeem; Mahmoud Badawy; Mostafa Elhosseini

doi:10.7717/peerj-cs.1070

An optimized deep learning approach for suicide detection through Arabic tweets

PeerJ Comput Sci. 2022 Aug 23:8:e1070. doi: 10.7717/peerj-cs.1070. eCollection 2022.

Authors

Nadiah A Baghdadi¹, Amer Malki², Hossam Magdy Balaha³, Yousry AbdulAzeem⁴, Mahmoud Badawy³, Mostafa Elhosseini^{2

3}

Affiliations

¹ Nursing Management and Education Department, College of Nursing, Princess Nourah bint Abdulrahman University, Riyadh, Saudi Arabia.
² College of Computer Science and Engineering, Taibah University, Yanbu, Saudi Arabia.
³ Computers and Control Systems Engineering Department, Faculty of Engineering, Mansoura University, Mansoura, Egypt.
⁴ Computer Engineering Department, Misr Higher Institute for Engineering and Technology, Mansoura, Egypt.

Abstract

Many people worldwide suffer from mental illnesses such as major depressive disorder (MDD), which affect their thoughts, behavior, and quality of life. Suicide is regarded as the second leading cause of death among teenagers when treatment is not received. Twitter is a platform for expressing their emotions and thoughts about many subjects. Many studies, including this one, suggest using social media data to track depression and other mental illnesses. Even though Arabic is widely spoken and has a complex syntax, depressive detection methods have not been applied to the language. The Arabic tweets dataset should be scraped and annotated first. Then, a complete framework for categorizing tweet inputs into two classes (such as Normal or Suicide) is suggested in this study. The article also proposes an Arabic tweet preprocessing algorithm that contrasts lemmatization, stemming, and various lexical analysis methods. Experiments are conducted using Twitter data scraped from the Internet. Five different annotators have annotated the data. Performance metrics are reported on the suggested dataset using the latest Bidirectional Encoder Representations from Transformers (BERT) and Universal Sentence Encoder (USE) models. The measured performance metrics are balanced accuracy, specificity, F1-score, IoU, ROC, Youden Index, NPV, and weighted sum metric (WSM). Regarding USE models, the best-weighted sum metric (WSM) is 80.2%, and with regards to Arabic BERT models, the best WSM is 95.26%.

Keywords: Deep Learning (DL); Machine Learning (ML); Suicide; Twitter.

Grants and funding

This work was supported by Princess Nourah bint Abdulrahman University, Researchers Supporting Project number (PNURSP2022R293), Princess Nourah bint Abdulrahman University, Riyadh, Saudi Arabia. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.