An optimized deep learning approach for suicide detection through Arabic tweets

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%.

A concentrated machine learning-based classification system for age-related macular degeneration (AMD) diagnosis using fundus images

“…Sensitivity indicates how well the model is able to identify good patterns 69 . It calculates the proportion of true positives out of all actual positives.…”

Precise Prostate Cancer Assessment Using IVIM-Based Parametric Estimation of Blood Diffusion from DW-MRI

“…Balanced Accuracy calculates the average of sensitivity and specificity. It provides an overall measure of the classifier’s performance that takes into account both true positive and true negative rates [ 60 ]. It is particularly useful when the dataset is imbalanced, as it accounts for uneven distribution of the classes.…”

Special issue on analysis and mining of social media data

“…As many as six articles focus on sentiment analysis for different purposes ( Smetanin, 2022 ; Pratama & Firmansyah, 2022 ; Baxi, Philip & Mago, 2022 ; Nguyen & Gokhale, 2022 ; Shamoi et al., 2022 ; Ali, Irfan & Lashari, 2023 ). Four studies focused on tackling online harms of different kinds, with studies on abusive language detection ( Almerekhi, Kwak & Jansen, 2022 ; Ramponi et al., 2022 ), suicidal ideation detection ( Baghdadi et al., 2022 ) and misinformation detection ( Obeidat et al., 2022 ). Others studied NLP techniques for social media , focused on the analysis of Twitter discourse ( Heaton et al., 2023 ), language identification ( Hidayatullah et al., 2023 ) and named entity recognition ( Fudholi et al., 2023 ).…”

“… Baghdadi et al. (2022) created a new Twitter dataset with Arabic tweets, where tweets are labelled as suicidal or not.…”