An Indonesian Mental Health Chatbot Model Based on A Sequence to Sequence LSTM
Keywords:
Dialogue response generation, long short-term memory, low-resource language, mental health chatbot, sequence to sequence modelAbstract
This research proposes an Indonesian-language mental health chatbot model based on the LSTM Sequence-to-Sequence (Seq2Seq) architecture as an adaptive initial support solution. Unlike static classification models, this generative approach aims to capture emotional dependencies and conversational context through context vectors. The research methodology utilizes the public PSYCHIKA dataset, which includes 5,667 conversation pairs a significant volume for a low-resource language. Evaluation was conducted by comparing 80:20 and 70:30 data split schemes. Experimental results showed the best performance with the 80:20 split, achieving a BLEU-1 score of 0.137, compared to the 70:30 split, which only reached 0.043. The model achieved stable convergence at 15–16 epochs via an early-stopping mechanism without any signs of overfitting. Although training stability was maintained, the low BLEU score confirms that the use of a pure Seq2Seq LSTM without an attention mechanism is not yet sufficient to generate highly fluent responses. These findings provide a reproducible technical baseline for the development of mental health dialogue systems in Indonesia, while also emphasizing the urgency of more advanced architectures to improve the quality of empathy in the future.References
[1] S. T. A. Noor, S. Siddique, O. Das, S. Yeasar, and R. B. Islam, “Exploring mental health disparities in Mozambique: Depression and anxiety symptoms among reproductive-aged women using data from Mozambique Demographic and Health Survey 2022–23,” Glob. Epidemiol., vol. 10, no. July, p. 100223, 2025, doi: 10.1016/j.gloepi.2025.100223.
[2] N. Ekawati, I. Riadi, and H. Yuliansyah, “Machine Learning-based Chatbot Model for Healthcare Service: A Bibliometric Analysis,” Aviat. Electron. Inf. Technol. Telecommun. Electr. Control., vol. 7, no. 3, p. 347, 2025, doi: 10.28989/avitec.v7i3.3050.
[3] A. Heidari, M. Esmaeilzadeh, and A. H. Mohammadi, “Tourism and mental health: Two raw diamonds awaiting their brilliance through mutual shaping,” Geopsychiatry, vol. 2, no. August, p. 100020, 2025, doi: 10.1016/j.geopsy.2025.100020.
[4] A. Muhariya, I. Riadi, and Y. Prayudi, “Cyberbullying Analysis on Instagram Using K-Means Clustering,” JUITA J. Inform., vol. 10, no. 2, p. 261, 2022, doi: 10.30595/juita.v10i2.14490.
[5] S. F. Handayani, D. Dairoh, and D. I. Af’idah, “Assessment of Retrieval and Generative Chatbots in Tourism Information Service,” JUITA J. Inform., vol. 13, no. 1, pp. 19–27, 2025, doi: 10.30595/juita.v13i1.24182.
[6] B. Yang, Y. Ding, C. Cui, and T. Guo, “A hybrid kernel principal component analysis and long short-term memory approach for EEG signal-based fatigue evaluation,” Alexandria Eng. J., vol. 131, no. October, pp. 209–217, 2025, doi: 10.1016/j.aej.2025.09.066.
[7] S. U. Singh and A. S. Namin, “A Survey on Chatbots and Large Language Models: Testing and Evaluation Techniques,” Nat. Lang. Process. J., 2025.
[8] H. Yuliansyah, H. A. Raihan, and Murinto, “Sentiment Analysis Model for VTuber Live Stream Chat using Decision Tree and Support Vector Machine,” J. Innov. Inf. Technol. Appl., vol. 7, no. 2, pp. 258–268, 2025, doi: 10.35970/jinita.v7i2.2872.
[9] I. Riadi, A. Fadlil, and M. Murni, “Identifying Hate Speech in Tweets with Sentiment Analysis on Indonesian Twitter Utilizing Support Vector Machine Algorithm,” Khazanah Inform. J. Ilmu Komput. dan Inform., vol. 9, no. 2, pp. 179–191, 2023, doi: 10.23917/khif.v9i2.22470.
[10] C. Lebeuf, M. A. Storey, and A. Zagalsky, “Software Bots,” IEEE Softw., vol. 35, no. 1, pp. 18–23, 2017, doi: 10.1109/MS.2017.4541027.
[11] A. Dwiyono, A. Abdiansah, and M. Fachrurrozi, “Analisis Perbandingan Klasifikasi Intent Chatbot Menggunakan Deep Learning BERT, RoBERTa, dan IndoBERT,” J. Inf. Syst. Res., vol. 6, no. 1, pp. 595–606, 2024, doi: 10.47065/josh.v6i1.6051.
[12] C. Xu, Y. Chen, Y. Tao, and W. Xie, “Deep learning-based detection of depression by fusing auditory, visual and textual clues,” J. Affect. Disord., vol. 391, no. July, p. 119860, 2025, doi: 10.1016/j.jad.2025.119860.
[13] A. A. Dzaky et al., “Optimization Chatbot Services Based on DNN-Bert for Mental Health of University Students,” J. Appl. Informatics Comput., vol. 8, no. 1, pp. 13–21, 2024, doi: 10.30871/jaic.v8i1.7403.
[14] A. Ilham Ardin and A. Salam, “Pengembangan Chatbot Kesehatan Mental Berbasis Web Menggunakan Model Long Short-Term Memory (LSTM),” Build. Informatics, Technol. Sci., vol. 7, no. 1, pp. 320–331, 2025, doi: 10.47065/bits.v7i1.7282.
[15] A. S. Rizky and E. Y. Hidayat, “Emotion Classification in Indonesian Text Using IndoBERT,” Comput. Eng. Appl., vol. 14, no. 1, pp. 2252–4274, 2025.
[16] A. Z. Kouzani and M. Nouman, “Detecting indicators of violence in digital text using deep learning,” Nat. Lang. Process. J., vol. 12, no. June, p. 100175, 2025, doi: 10.1016/j.nlp.2025.100175.
[17] M. Zulfadhilah, Y. Prayudi, and I. Riadi, “Cyber Profiling Using Log Analysis And K-Means Clustering,” Int. J. Adv. Comput. Sci. Appl., vol. 7, no. 7, pp. 430–435, 2016, doi: 10.14569/ijacsa.2016.070759.
[18] T. Y. Chen, Y. C. Chiu, N. Bi, and R. T. H. Tsai, “Multi-Modal Chatbot in Intelligent Manufacturing,” IEEE Access, vol. 9, pp. 82118–82129, 2021, doi: 10.1109/ACCESS.2021.3083518.
[19] B. Babayigit, H. Rahmani, and M. Abubaker, “TrBot: A Turkish Deep Learning Chatbot Utilizing Seq2Seq Model,” IEEE Access, vol. 13, no. February, pp. 49552–49566, 2025, doi: 10.1109/ACCESS.2025.3550852.
[20] Hariani and I. Riadi, “Detection of Cyberbullying on Social Media Using Data Mining Techniques,” Metall. Mater. Eng., vol. 31, no. 4, pp. 894–899, 2025, doi: 10.63278/1530.
[21] M. Ghaseminejad Raeini, “The evolution of language models: From N-Grams to LLMs, and beyond,” Nat. Lang. Process. J., vol. 12, no. June, p. 100168, 2025, doi: 10.1016/j.nlp.2025.100168.
[22] Z. Liu, Y. Quan, X. Lyu, and M. J. F. Alenazi, “Enhancing Clinical Accuracy of Medical Chatbots With Large Language Models,” IEEE J. Biomed. Heal. Informatics, vol. 29, no. 9, pp. 6395–6405, 2025, doi: 10.1109/JBHI.2024.3470323.
[23] M. Clark and S. Bailey, “Chatbots in Health Care: Connecting Patients to Information,” Can. J. Heal. Technol., vol. 4, no. 1, pp. 1–22, 2024, doi: 10.51731/cjht.2024.818.
[24] C. B. Nordheim, A. Følstad, and C. A. Bjørkli, “An Initial Model of Trust in Chatbots for Customer Service - Findings from a Questionnaire Study,” Interact. Comput., vol. 31, no. 3, pp. 317–335, 2019, doi: 10.1093/iwc/iwz022.
[25] R. Yang, M. Fu, C. Tantithamthavorn, C. Arora, L. Vandenhurk, and J. Chua, “RAGVA: Engineering retrieval augmented generation-based virtual assistants in practice,” J. Syst. Softw., vol. 226, no. August 2024, p. 112436, 2025, doi: 10.1016/j.jss.2025.112436.
[26] A. A. Firdaus, A. Yudhana, I. Riadi, and Mahsun, “Indonesian presidential election sentiment: Dataset of response public before 2024,” Data Br., vol. 52, p. 109993, 2024, doi: 10.1016/j.dib.2023.109993.
[27] B. K. Yazar and E. Kilic, “Improving Low-Resource Kazakh-English and Turkish-English Neural Machine Translation Using Transfer Learning and Part of Speech Tags,” IEEE Access, vol. 13, no. January, pp. 32341–32356, 2025, doi: 10.1109/ACCESS.2025.3542491.
[28] H. Bichri, A. Chergui, and M. Hain, “Investigating the Impact of Train / Test Split Ratio on the Performance of Pre-Trained Models with Custom Datasets,” Int. J. Adv. Comput. Sci. Appl., vol. 15, no. 2, pp. 331–339, 2024, doi: 10.14569/IJACSA.2024.0150235.
[29] H. Guo and T. Erdenebold, “Factors influencing intention to adopt an AI chatbot for learning in higher education: An integrated PLS-SEM, IPMA, and ANN approach,” Comput. Educ. Artif. Intell., vol. 9, no. 51, p. 100477, 2025, doi: 10.1016/j.caeai.2025.100477.
[30] G. A. Santos, G. G. de Andrade, G. R. S. Silva, F. C. M. Duarte, J. P. J. Da Costa, and R. T. de Sousa, “A Conversation-Driven Approach for Chatbot Management,” IEEE Access, vol. 10, pp. 8474–8486, 2022, doi: 10.1109/ACCESS.2022.3143323.
[31] A. R. Mandli, S. Rajput, and T. Sharma, “COMET: Generating commit messages using delta graph context representation,” J. Syst. Softw., vol. 222, no. January 2024, p. 112307, 2025, doi: 10.1016/j.jss.2024.112307.
[32] M. Ahmed, H. U. Khan, and E. U. Munir, “Conversational AI: An Explication of Few-Shot Learning Problem in Transformers-Based Chatbot Systems,” IEEE Trans. Comput. Soc. Syst., vol. 11, no. 2, pp. 1888–1906, 2024, doi: 10.1109/TCSS.2023.3281492.
[33] Q. Liu, J. Huang, L. Wu, K. Zhu, and S. Ba, “CBET: design and evaluation of a domain-specific chatbot for mobile learning,” Univers. Access Inf. Soc., vol. 19, no. 3, pp. 655–673, 2020, doi: 10.1007/s10209-019-00666-x.
[34] Supriyono, A. P. Wibawa, Suyono, and F. Kurniawan, “Advancements in natural language processing: Implications, challenges, and future directions,” Telemat. Informatics Reports, vol. 16, no. April, p. 100173, 2024, doi: 10.1016/j.teler.2024.100173.
[35] A. Ohashi and R. Higashinaka, “Adapting language generation to dialogue environments and users for task-oriented dialogue systems,” Nat. Lang. Process. J., vol. 11, no. March, p. 100153, 2025, doi: 10.1016/j.nlp.2025.100153.
[36] L. C. Navarro, S. S. Mucciaccia, F. Mutz, T. M. Paixäo, and C. Badue, “Exploring question answering: metric analysis and evaluation framework for enhanced interpretability,” Neural Comput. Appl., vol. 38, no. 9, 2026, doi: 10.1007/s00521-026-12053-8.
[37] Y. Zhu, S. Lu, L. Zheng, J. Guo, and W. Zhang, Texygen: A Benchmarking Platform for Text Generation Models. 2018.
[38] K. Papineni, S. Roukos, T. Ward, and W.-J. Zhu, “BLEU: a Method for Automatic Evaluation of Machine Translation,” Ann. Phys., vol. 371, no. 23, pp. 437–461, 1922, doi: 10.1002/andp.19223712302.
[39] D. Escobar-Grisales, J. C. Vásquez-Correa, and J. R. Orozco-Arroyave, “Evaluation of effectiveness in conversations between humans and chatbots using parallel convolutional neural networks with multiple temporal resolutions,” Multimed. Tools Appl., vol. 83, no. 2, pp. 5473–5492, 2024, doi: 10.1007/s11042-023-14896-y.
[40] C. Luna-Jiménez, M. Gil-Martín, L. F. D’Haro, F. Fernández-Martínez, and R. San-Segundo, “Evaluating emotional and subjective responses in synthetic art-related dialogues: A multi-stage framework with large language models,” Expert Syst. Appl., vol. 255, no. PB, p. 124524, 2024, doi: 10.1016/j.eswa.2024.124524.
[41] M. Adam, M. Wessel, and A. Benlian, “AI-based chatbots in customer service and their effects on user compliance,” Electron. Mark., vol. 31, no. 2, pp. 427–445, 2021, doi: 10.1007/s12525-020-00414-7.
[42] B. O. S. Miranda, H. Yuliansyah, and M. K. Biddinika, “Machine Translation Indonesian Bengkulu Malay Using Neural Machine Translation-LSTM,” IJCCS (Indonesian J. Comput. Cybern. Syst., vol. 18, no. 3, 2024, doi: 10.22146/ijccs.98384.
[43] F. Benedict, C. V. Mramba, S. Kaaya, J. Kimaro, J. N. Baumgartner, and M. Bachmann, “Developing a regional mental health plan for Dar es Salaam, Tanzania: Results from a situational analysis, qualitative inquiry, and stakeholder engagement process,” SSM - Ment. Heal., vol. 8, no. September, p. 100532, 2025, doi: 10.1016/j.ssmmh.2025.100532.
[44] A. Jha, A. Bhatia, K. Tiwari, and H. M. Pandey, “Hierarchical Bayesian Deep Learning for return on advertising spend prediction: A probabilistic approach to e-commerce advertising,” Eng. Appl. Artif. Intell., vol. 164, no. PA, p. 113200, 2026, doi: 10.1016/j.engappai.2025.113200.
[45] P. Rathnayaka, N. Mills, D. Burnett, D. De Silva, D. Alahakoon, and R. Gray, “A Mental Health Chatbot with Cognitive Skills for Personalised Behavioural Activation and Remote Health Monitoring,” Sensors, vol. 22, no. 10, 2022, doi: 10.3390/s22103653.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Nia Ekawati, Nia Ekawati, Imam Riadi, Herman Yuliansyah
This work is licensed under a Creative Commons Attribution 4.0 International License.
JUITA: Jurnal Informatika is licensed under a Creative Commons Attribution 4.0 International License.
