Rohini Kancharapu; G.V.Hindumathi; Sravya Pallantla

Multi-Model Ensemble-based Machine Learning Approach for Enhanced Suicidal Ideation Detection on Twitter Posts

PDF (1378KB), PP.15-36

Views: 0 Downloads: 0

Author(s)

Rohini Kancharapu ^1,* G.V.Hindumathi ² Sravya Pallantla ²

1. Department of Computer Science and Engineering, Gayatri Vidya Parishad College of Engineering for Women (A), Kommadi, Visakhapatnam-530048, Andhra Pradesh, India

2. Department of Computer Science and Engineering, Gayatri Vidya Parishad College of Engineering (A) Kommadhi, Visakhapatnam 530048, Andhra Pradesh, India

* Corresponding author.

DOI: https://doi.org/10.5815/ijmecs.2026.05.02

Received: 28 Jan. 2025 / Revised: 15 May 2025 / Accepted: 30 Jan. 2026 / Published: 8 Oct. 2026

Index Terms

Machine Learning, Fake News Detection, Suicidal Tweets, Ensemble Models, BERT Sentiment Analysis.

Abstract

Identifying suicidal ideation on Twitter is crucial for timely intervention and suicide prevention efforts. This study leverages Twitter data to identify individuals contemplating suicide, addressing the challenge of distinguishing genuine suicidal ideations from those posted for entertainment. Given the rise in depression and anxiety, particularly among the youth, an ensemble model combining various machine learning algorithms is proposed to enhance the accuracy of detecting genuine suicidal tweets. The ensemble model integrates the predictions of multiple internal models: Logistic Regression, LinearSVC, XGBoost, Naive Bayes, and Random Forest. Each model generates a prediction based on extracted features from the tweets, and the final prediction is determined by calculating the weighted average of these predictions, considering the relative importance of each model. If this weighted average exceeds a predefined threshold, the tweet is classified as non-suicidal; otherwise, it is classified as suicidal. This methodology allows the ensemble model to balance the strengths and weaknesses of individual models, resulting in a robust and accurate classifier. Incorporating BERT classification and VADER sentiment analysis, the model is trained on labeled data to capture intricate patterns in tweet embeddings. Evaluated against various performance metrics, the ensemble model achieves an accuracy of 95.81%, precision of 93.45%, recall of 89.90%, and an F1-score of 94.68%, significantly outperforming individual models. The model also demonstrates a superior AUC-ROC value of 0.95, indicating excellent performance in distinguishing between classes. This approach not only advances the current methodologies but also contributes to public health by enhancing the reliability of suicide prevention efforts on social media platforms.

Cite This Paper

Rohini Kancharapu, G. V. Hindumathi, Sravya Pallantla, "Multi-Model Ensemble-based Machine Learning Approach for Enhanced Suicidal Ideation Detection on Twitter Posts", International Journal of Modern Education and Computer Science(IJMECS), Vol.18, No.5, pp. 15-36, 2026. DOI:10.5815/ijmecs.2026.05.02

Reference

[1]Mazhar Javed, Awais Yasin, Haitham Nobanee, Ahmed Abid Ali, Zain Shahzad, Muhammad Nabeel, et. al., Fake News Data Exploration and Analytics. Electronics 10(19):2326. doi: 10.3390/electronics10192326, 2021.
[2]V. V. Hirlekar and A. Kumar , Natural Language Processing based Online Fake News Detection Challenges – A Detailed Review. 5th International Conference on Communication and Electronics Systems (ICCES) pp. 748-754 doi: 10.1109/ICCES48766.2020.9137915, 2020.
[3]R. Hassan and Md. R. Islam, Detection of fake online reviews using semi-supervised and supervised learning. 2019 International Conference on Electrical, Computer and Communication Engineering (ECCE) pp. 1–5. doi: 10.1109/ECACE.2019.8679186, 2019.
[4]V. Sivasangari, Ashok Kumar Mohan, K. Suthendran and M. Sethumadhavan, Isolating Rumors Using Sentiment Analysis. Journal of Cyber Security and Mobility, 7(1):pp. 181-200. doi: 10.13052/jcsm2245-1439.7113, 2018.
[5]S. B. Parikh and P. K. Atrey, Media-Rich Fake News Detection: A Survey. IEEE Conference on Multimedia Information Processing and Retrieval (MIPR) pp. 436–441. doi: 10.1109/MIPR.2018.00093, 2018.
[6] Rodrigues Anisha P, Fernandes Roshan, A Aakash, B Abhishek, Shetty Adarsh, K Atul et. al., Real-Time Twitter Spam Detection and Sentiment Analysis using Machine Learning and Deep Learning Techniques. Intell. Neuroscience. pp. 1–14. doi: 10.1155/2022/5211949, 2022.
[7]Du Jingcheng , Yaoyun Zhang , Jianhong Luo, Yuxi Jia, Qiang Wei, Cui Tao, Hua Xu , Extracting psychiatric stressors for suicide from social media using deep learning. BMC Med Inform Decis Mak 18(Suppl 2),pp 43 doi.org/10.1186/s12911-018-0632-8, 2018.
[8]S. Ni, J. Li, and H.-Y. Kao, MVAN: Multi-View Attention Networks for Fake News Detection on Social Media IEEE Access, 9: pp. 106907–106917. doi: 10.1109/ACCESS.2021.3100245, 2021.
[9]D. V. B. De Oliveira and U. P. Albuquerque, Cultural Evolution and Digital Media: Diffusion of Fake News About COVID-19 on Twitter SN COMPUT. SCI., 2(6): p. 430, doi: 10.1007/s42979-021-00836-w, 2021.
[10]S. G. Taskin, E. U. Kucuksille, and K. Topal , Detection of Turkish Fake News in Twitter with Machine Learning Algorithms Arab J Sci Eng. 47(2): pp. 2359–2379. doi: 10.1007/s13369-021-06223-0, 2022.
[11]J. C. S. Reis, A. Correia, F. Murai, A. Veloso, and F. Benevenuto, Supervised Learning for Fake News Detection IEEE Intell. Syst., vol. 34(2): pp. 76–81. doi: 10.1109/MIS.2019.2899143, 2019.
[12]N. V. Babu and E. G. M. Kanaga , Sentiment Analysis in Social Media Data for Depression Detection Using Artificial Intelligence: A Review SN COMPUT. SCI., 3(1):p. 74. doi: 10.1007/s42979-021-00958-1, 2022.
[13]A. Alsaeedi and M. Al-Sarem, Detecting Rumors on Social Media Based on a CNN Deep Learning Technique Arab J Sci Eng, 45(12):pp. 10813–10844. doi: 10.1007/s13369-020-04839-2, 2020.
[14]M. Umer, Z. Imtiaz, S. Ullah, A. Mehmood, G. S. Choi, Fake News Stance Detection Using Deep Learning Architecture (CNN-LSTM) IEEE Access, 8: pp. 156695–156706. doi: 10.1109/ACCESS.2020.3019735, 2020.
[15]R. Ahuja and S. C. Sharma , Transformer-Based Word Embedding With CNN Model to Detect Sarcasm and Irony Arab J Sci Eng, vol. 47(8): pp. 9379–9392. doi: 10.1007/s13369-021-06193-3, 2022.
[16]J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding Proceedings of NAACL-HLT 2019, Minneapolis, ACL, vol. 1, pp. 4171–4186. doi: 10.18653/v1/N19-1423, 2019.
[17]M. F. Mridha, A. J. Keya, Md. A. Hamid, M. M. Monowar, and Md. S. Rahman , A Comprehensive Review on Fake News Detection With Deep Learning IEEE Access 9:pp. 156151–156170. doi: 10.1109/ACCESS.2021.3129329, 2021.
[18]M. A. Alonso, D. Vilares, C. Gómez-Rodríguez, and J. Vilares, Sentiment Analysis for Fake News Detection Electronics, 10(11): p. 1348. doi: 10.3390/electronics10111348, 2021.
[19]Z. Khanam, B. N. Alwasel, H. Sirafi, and M. Rashid, Fake News Detection Using Machine Learning Approaches IOP Conf. Ser.: Mater. Sci. Eng. 1099(1): p. 012040. doi: 10.1088/1757-899X/1099/1/012040, 2021.
[20]W. Antoun, F. Baly, R. Achour, A. Hussein, and H. Hajj, State of the Art Models for Fake News Detection Tasks 2020 IEEE International Conference on Informatics, IoT, and Enabling Technologies (ICIoT) pp. 519–524. doi: 10.1109/ICIoT48696.2020.9089487, 2020.
[21]R. K. Kaliyar, A. Goswami, and P. Narang, FakeBERT: Fake news detection in social media with a BERT-based deep learning approach Multimed Tools Appl. 80(8): pp. 11765–11788. doi: 10.1007/s11042-020-10183-2, 2021.
[22]K. Xu, F. Wang, H. Wang, and B. Yang, Detecting fake news over online social media via domain reputations and content understanding Tsinghua Sci. Technol. 25(1):, pp. 20–27. doi: 10.26599/TST.2018.9010139, 2020.
[23]R. Haque, N. Islam, M. Islam, and M. M. Ahsan, A Comparative Analysis on Suicidal Ideation Detection Using NLP, Machine, and Deep Learning Technologies, 10(3):p. 57. doi: 10.3390/technologies10030057, 2022.
[24]P. M. Konkobo, R. Zhang, S. Huang, T. T. Minoungou, J. A. Ouedraogo, and L. Li, A Deep Learning Model for Early Detection of Fake News on Social Media 2020 7th International Conference on Behavioural and Social Computing (BESC) pp. 1–6. doi: 10.1109/BESC51023.2020.9348311, 2020.
[25]S. T. Rabani, Q. R. Khan, and A. M. U. D. Khanday, Detection of Suicidal Ideation on Twitter using Machine Learning & Ensemble Approaches Baghdad Sci.J, vol. 17(4): p. 1328. doi: 10.21123/bsj.2020.17.4.1328, 2020.
[26]S. T. Rabani, Q. R. Khan, and A. M. U. D. Khanday, A Novel Approach To Predict The Level Of Suicidal Ideation On Social Networks Using Machine And Ensemble Learning ICTACT Journal on Soft Computing 11(2):pp. 2288-2293. doi: 10.21917/ijsc.2021.0327, 2021.
[27]Kancharapu R and Ayyagari Srinagesh, A comparative study on word embedding techniques for suicide prediction on COVID-19 tweets using deep learning models Int. j. inf. tecnol.15(6):pp. 3293–3306. doi: 10.1007/s41870-023-01338-z, 2023.
[28]Kancharapu R, A. SriNagesh, and M. BhanuSridhar, Prediction of Human Suicidal Tendency based on Social Media using Recurrent Neural Networks through LSTM. 2022 International Conference on Computing, Communication and Power Technology (IC3P). pp. 123–128. doi: 10.1109/IC3P52835.2022.00033, 2022.

International Journal of Modern Education and Computer Science (IJMECS)