A comparative analysis of machine learning, deep learning, and ensemble learning models for suicidal ideation detection on social media
4 affiliations
- 1Faculty of Computing and Software Engineering, Arba Minch University, Arba Minch, Ethiopia.
- 2College of Engineering and Technology, Bonga University, Bonga, Ethiopia.
- 3Expat Professor, Arba Minch University, Arba Minch, Ethiopia.
- 4Faculty of Computing and Informatics, Jimma University, Jimma, Ethiopia.
Abstract
Suicidal ideation is the consideration of self-inflicted death and has emerged as a serious and rising concern for worldwide public health systems, contributing to over 800,000 deaths annually worldwide. Individuals express intentions, distress, and thoughts of self-harm and death, thereby offering a crucial and unprecedented avenue for timely psychological intervention and surveillance. The core problem addressed by this research is the pronounced global insufficiency in detecting and mitigating suicidal ideation across linguistically diverse environments, specifically focusing on low-resource languages. Previous computational studies have primarily focused on English and other widely used languages, leaving a critical research gap for contexts such as Amharic. The main aim of this study was to investigate and to develop a robust and optimal deep learning model for identifying suicidal ideation in Amharic social media content. A total of 5,428 postings from social media such as Facebook and Telegram were carefully collected, manually annotated, and processed to provide the first publicly available dataset on Amharic suicidal ideation. After preprocessing, Word2Vec, GloVe, and FastText were among the word embedding techniques used for feature engineering. Five deep learning models and four machine learning models were then compared in this study. Based on the experimental results, ensemble learning models achieved slightly higher performance than the individual deep learning models in suicidal ideation detection. Specifically, hard voting ensemble learning models achieved the highest accuracy (83.3%) and precision (86.55%). CNN-BiLSTM achieved an accuracy of 81.45%, while the BiLSTM model achieved an accuracy of 81.4%, indicating that bidirectional sequence learning effectively captures contextual information in Amharic texts. Beyond its strong empirical performance, this study contributes a robust detection framework and introduces a public Amharic dataset, thereby establishing a foundational methodological resource for mental health research. Future studies should focus on developing scalable datasets and context-aware deep learning models that effectively handle multimodal data, multilingual transformer models, fusion-based features, and addressing bias in low-resource computational linguistics.
Related
- Comparative evaluation of machine learning algorithms for Maize Lethal Necrosis Disease detection under class imbalance
- Multimodal Magnetic Resonance Imaging Biomarkers of Pediatric Traumatic Brain Injury Identified by Ensemble Learning Are Associated with Psychopathology
- Spatial Prediction of Opisthorchis viverrini Infection Risk Using Multi-Source Remote Sensing, Hexagonal Grid Optimization, and Ensemble Machine Learning: A Case Study From Northeastern Thailand.
- SIMORGH: Ensemble-Aware Geometric Deep Learning for Apo-State and Cryptic Ligand Binding Site Prediction
- Style transfer mapping with ensemble learning for cross-subject EEG-based neuropsychiatric disease recognition.
BibTeX
@article{woldegiorgis2026comparative,
title = {{A comparative analysis of machine learning, deep learning, and ensemble learning models for suicidal ideation detection on social media}},
author = {Andualem Woldegiorgis and Mohammed Abebe and Durga Prasad Sharma and Worku Jimma},
journal = {PLOS Mental Health},
year = {2026},
month = oct,
doi = {10.1371/journal.pmen.0000721},
url = {https://journals.plos.org/mentalhealth/article?id=10.1371/journal.pmen.0000721},
note = {CC BY},
}
RIS
TY - JOUR
TI - A comparative analysis of machine learning, deep learning, and ensemble learning models for suicidal ideation detection on social media
AU - Andualem Woldegiorgis
AU - Mohammed Abebe
AU - Durga Prasad Sharma
AU - Worku Jimma
PY - 2026
DA - 2026/10/22
JO - PLOS Mental Health
DO - 10.1371/journal.pmen.0000721
UR - https://journals.plos.org/mentalhealth/article?id=10.1371/journal.pmen.0000721
AB - Suicidal ideation is the consideration of self-inflicted death and has emerged as a serious and rising concern for worldwide public health systems, contributing to over 800,000 deaths annually worldwide. Individuals express intentions, distress, and thoughts of self-harm and death, thereby offering a crucial and unprecedented avenue for timely psychological intervention and surveillance. The core problem addressed by this research is the pronounced global insufficiency in detecting and mitigating suicidal ideation across linguistically diverse environments, specifically focusing on low-resource languages. Previous computational studies have primarily focused on English and other widely used languages, leaving a critical research gap for contexts such as Amharic. The main aim of this study was to investigate and to develop a robust and optimal deep learning model for identifying suicidal ideation in Amharic social media content. A total of 5,428 postings from social media such as Facebook and Telegram were carefully collected, manually annotated, and processed to provide the first publicly available dataset on Amharic suicidal ideation. After preprocessing, Word2Vec, GloVe, and FastText were among the word embedding techniques used for feature engineering. Five deep learning models and four machine learning models were then compared in this study. Based on the experimental results, ensemble learning models achieved slightly higher performance than the individual deep learning models in suicidal ideation detection. Specifically, hard voting ensemble learning models achieved the highest accuracy (83.3%) and precision (86.55%). CNN-BiLSTM achieved an accuracy of 81.45%, while the BiLSTM model achieved an accuracy of 81.4%, indicating that bidirectional sequence learning effectively captures contextual information in Amharic texts. Beyond its strong empirical performance, this study contributes a robust detection framework and introduces a public Amharic dataset, thereby establishing a foundational methodological resource for mental health research. Future studies should focus on developing scalable datasets and context-aware deep learning models that effectively handle multimodal data, multilingual transformer models, fusion-based features, and addressing bias in low-resource computational linguistics.
SN - 2837-8156
ER -