Suicidal Ideation Detection on Twitter in Indonesia: A Comparative Transfer Learning Study using IndoBERT and Multilingual BERT
DOI:
https://doi.org/10.52436/1.jutif.2026.7.4.5652Keywords:
IndoBERT, Indonesian language, Multilingual BERT, Natural language processing, Suicidal ideation, Transfer learningAbstract
The effectiveness of suicide prevention in Indonesia is severely hindered by significant underreporting and social stigma, leading at-risk individuals to express their distress on social media platforms such as Twitter. However, detecting these signals is computationally challenging due to the informal nature of Indonesian slang and the risk of losing emotional context through aggressive pre-processing. This study aims to evaluate the performance of various deep learning and traditional models in detecting suicidal ideation while specifically analyzing the impact of syntactic preservation. We performed a comparative analysis using IndoBERT, Multilingual BERT (mBERT), and three baseline models including Logistic Regression, Support Vector Machine, and Random Forest which were evaluated through two distinct pre-processing strategies, namely Dataset A (fully preprocessed) and Dataset B (partially preprocessed). Experimental results demonstrate that IndoBERT achieved the highest performance on Dataset B with an accuracy of 90.6%, outperforming traditional baselines. The results indicate that omitting stopword removal and stemming is more effective for transformer-based architectures, as retaining original word forms helps preserve semantic integrity and emotional nuances required for contextual understanding. These findings highlight the importance of context-aware solutions to bridge the data gap in public health. By providing a robust computational framework that maintains linguistic integrity, this research has the potential to facilitate scalable, real-time interventions for supporting the identification of high-risk individuals within the Indonesian digital landscape. This study contributes to the development of automated mental health screening tools by demonstrating the potential of NLP-based methods for detecting psychological distress in low-resource, informal languages.
Downloads
References
WHO, W. H. Organization, Ed. Suicide worldwide in 2019. 2021, p. 35.
K. Saha, J. Torous, S. K. Ernala, C. Rizuto, A. Stafford, and M. De Choudhury, "A computational study of mental health awareness campaigns on social media," Translational Behavioral Medicine, vol. 9, no. 6, pp. 1197-1207, 2019, doi: 10.1093/tbm/ibz028.
R. Runcan, "Suicide in Adolescence: A Review of Literature," vol. 19, no. 3, pp. 109-120, 2020.
M. Imonova, "Causes of Suicide Tendency in Adolescents," Journal of Discoveries in Applied and Natural Science, vol. 1, no. 1, pp. 62-67, 2023.
E. D. Klonsky, A. M. May, and B. Y. Saffer, "Suicide, Suicide Attempts, and Suicidal Ideation," Annual Review of Clinical Psychology, vol. 12, no. 1, pp. 307-330, 2016, doi: 10.1146/annurev-clinpsy-021815-093204.
A. A. M. Hubers et al., "Suicidal ideation and subsequent completed suicide in both psychiatric and non-psychiatric populations: a meta-analysis," Epidemiology and Psychiatric Sciences, vol. 27, no. 2, pp. 186-198, 2018, doi: 10.1017/S2045796016001049.
E. A. Swedo et al., "Associations Between Social Media and Suicidal Behaviors During a Youth Suicide Cluster in Ohio," Journal of Adolescent Health, vol. 68, no. 2, pp. 308-316, 2021/02/01/ 2021, doi: 10.1016/j.jadohealth.2020.05.049.
C. Intachomphoo, Social Media and Youth Suicide: A Systematic Review. 2018.
S. Onie et al., "Indonesia's first suicide statistics profile: an analysis of suicide and attempt rates, underreporting, geographic distribution, gender, method, and rurality," The Lancet Regional Health - Southeast Asia, vol. 22, no. 1, pp. 1-10, 2024, doi: 10.1016/j.lansea.2024.100368.
N. Hartini, N. A. Fardana, A. D. Ariana, and N. D. Wardana, "Stigma toward people with mental health problems in Indonesia," Psychology Research and Behavior Management, vol. 11, no. 1, pp. 535-541, 2018/10/31 2018, doi: 10.2147/PRBM.S175251.
K. M. Carley, M. M. Malik, M. Kowalchuck, J. Pfeffer, and P. Landwehr, "Twitter usage in Indonesia," Available at SSRN 2720332, vol. 1, no. 1, pp. 1-62, 2015, doi: 10.2139/ssrn.2720332.
Z. Wang, M. Jin, and Y. Lu, "High-Precision Detection of Suicidal Ideation on Social Media Using Bi-LSTM and BERT Models," in Cognitive Computing – ICCC 2023, Cham, 2024, vol. 1, no. 1: Springer Nature Switzerland, pp. 3-18, doi: 10.1007/978-3-031-51671-9_1.
O. Akintoye, N. Wei, and Q. Liu, "Suicide Detection in Tweets Using LSTM and Transformers," in 2024 4th Asia Conference on Information Engineering (ACIE), 2024, vol. 1, no. 1, pp. 22-27, doi: 10.1109/ACIE61839.2024.00011.
G. Ananthakrishnan, A. K. Jayaraman, T. E. Trueman, S. Mitra, K. A. A, and A. Murugappan, "Suicidal Intention Detection in Tweets Using BERT-Based Transformers," in 2022 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS), 2022, vol. 1, no. 2, pp. 322-327, doi: 10.1109/ICCCIS56430.2022.10037677.
R. B. Soudi, M. S. Zaghloul, and O. M. Badawy, "Framework for suicide detection from Arabic tweets using deep learning," in 2022 32nd International Conference on Computer Theory and Applications (ICCTA), 2022, vol. 1, no. 1, pp. 96-103, doi: 10.1109/ICCTA58027.2022.10206145.
U. Naseem, M. Khushi, J. Kim, and A. G. Dunn, "Hybrid Text Representation for Explainable Suicide Risk Identification on Social Media," IEEE Transactions on Computational Social Systems, vol. 11, no. 4, pp. 4663-4672, 2024, doi: 10.1109/TCSS.2022.3184984.
W. Zeng and Y. Wu, "Attention-based BiLSTM Network for Social Media Suicide Detection," presented at the Proceedings of the 2023 4th International Symposium on Artificial Intelligence for Medicine Science, Chengdu, China, 2024. [Online]. Available: https://doi.org/10.1145/3644116.3644236.
M. F. F. Mardianto, B. S. Pratama, M. Audilla, and E. Pusporani, "Sentiment Analysis of Suicide on X Using Support Vector Machine and Naive Bayes Classifier Algorithms," INTENSIF: Jurnal Ilmiah Penelitian dan Penerapan Teknologi Sistem Informasi, vol. 9, no. 1, pp. 60-75, 2025, doi: 10.29407/intensif.v9i1.23742.
P. Karmakar and C. M. Turjo, "Detecting Suicide Risk Across Social Media Platforms: Comparing Traditional and Deep Learning Approaches," in 2025 International Conference on Quantum Photonics, Artificial Intelligence, and Networking (QPAIN), 31 July-2 Aug. 2025 2025, pp. 1-6, doi: 10.1109/QPAIN66474.2025.11172223.
C. T. Oyewale, J. D. Akinyemi, A. O. J. Ibitoye, and O. F. W. Onifade, "Predicting Suicide Ideation from Social Media Text Using CNN-BiLSTM," in Soft Computing and Its Engineering Applications, Cham, K. K. Patel, K. C. Santosh, A. Patel, and A. Ghosh, Eds., 2024: Springer Nature Switzerland, pp. 274-286.
M. D. Setiawan, S. Kimberly, F. A. Suharjo, and J. Harefa, "Transfer Learning using IndoBERT with Long Short-Term Memory Classifier for Detection of Suicide Ideation Themed Indonesian Twitter Posts," in 2024 4th International Conference of Science and Information Technology in Smart Administration (ICSINTESA), 2024, vol. 1, no. 1, pp. 276-281, doi: 10.1109/ICSINTESA62455.2024.10747816.
S. Chancellor and M. De Choudhury, "Methods in predictive techniques for mental health status on social media: a critical review," npj Digital Medicine, vol. 3, no. 1, p. 43, 2020, doi: 10.1038/s41746-020-0233-7.
F. Koto, A. Rahimi, J. H. Lau, and T. Baldwin, "IndoLEM and IndoBERT: A benchmark dataset and pre-trained language model for Indonesian NLP," International Committee on Computational Linguistics, vol. 1, no. 1, pp. 757–770, 2020, doi: 10.18653/v1/2020.coling-main.66.
J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, "BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding," 2018, doi: 10.18653/v1/N19-1423.
B. Wilie et al., "IndoNLU: Benchmark and resources for evaluating Indonesian natural language understanding," Association for Computational Linguistics, vol. 1, no. 1, pp. 843–857, 2020, doi: 10.18653/v1/2020.aacl-main.85.
T. Pires, E. Schlinger, and D. Garrette, "How Multilingual is Multilingual BERT?," Florence, Italy, July 2019: Association for Computational Linguistics, in Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 4996-5001, doi: 10.18653/v1/P19-1493.
A. Vaswani et al., "Attention Is All You Need," 06/12 2017, doi: 10.48550/arXiv.1706.03762.
D. Osinga, Deep learning cookbook: practical recipes to get started quickly. " O'Reilly Media, Inc.", 2018.
Y. Song, J. Wang, Z. Liang, L. Zhiyue, and T. Jiang, "Utilizing BERT Intermediate Layers for Aspect Based Sentiment Analysis and Natural Language Inference," vol. 1, no. 1, pp. 380–385, 2020, doi: 10.48550/arXiv.2002.04815.
S. A. Rauf, Y. Qiang, S. B. Ali, and W. Ahmad, "Using bert for checking the polarity of movie reviews," International Journal of Computer Applications, vol. 177, no. 21, pp. 37-41, 2019, doi: 10.5120/ijca2019919675.
C. Sun, X. Qiu, Y. Xu, and X. Huang, "How to Fine-Tune BERT for Text Classification?," in Chinese Computational Linguistics, Cham, M. Sun, X. Huang, H. Ji, Z. Liu, and Y. Liu, Eds., 2019, vol. 1, no. 1: Springer International Publishing, pp. 194-206, doi: 10.1007/978-3-030-32381-3_16.
M. R. Yanuar and S. Shiramatsu, "Aspect Extraction for Tourist Spot Review in Indonesian Language using BERT," in 2020 International Conference on Artificial Intelligence in Information and Communication (ICAIIC), 19-21 Feb. 2020 2020, vol. 1, no. 1, pp. 298-302, doi: 10.1109/ICAIIC48513.2020.9065263.
W. Maharani, "Sentiment Analysis during Jakarta Flood for Emergency Responses and Situational Awareness in Disaster Management using BERT," in 2020 8th International Conference on Information and Communication Technology (ICoICT), 2020, vol. 1, no. 1, pp. 1-5, doi: 10.1109/ICoICT49345.2020.9166407.
Additional Files
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Wiyan Herra Herviana, Retno Kusumaningrum, Bayu Surarso
This work is licensed under a Creative Commons Attribution 4.0 International License.
</a
