Reliable Intent Detection in Public Service Chatbots Using Hybrid IndoBERT and Bidirectional Long Short-Term Memory with Confidence-Based Decision Strategy
DOI:
https://doi.org/10.52436/1.jutif.2026.7.3.5794Keywords:
Chatbot, Confidence-Based Decision, Hybrid NLP, IndoBERT, Intent Detection, LSTMAbstract
The rapid digitalization of public services has increased the demand for intelligent information systems capable of providing accurate and responsive assistance to citizens on a 24/7 basis. However, many existing public service chatbots still rely on rule-based mechanisms or single-model natural language processing (NLP) approaches, which often fail to handle linguistic variations, informal expressions, and ambiguous user queries. This study proposes a Hybrid Natural Language Understanding (NLU) architecture that integrates a fine-tuned IndoBERT model with a Bidirectional Long Short-Term Memory (BiLSTM) network to improve intent detection performance in public service chatbots. To enhance system reliability, a confidence-based decision-making mechanism is introduced, enabling the system to dynamically select the most reliable prediction or activate a fallback pattern-matching module when confidence thresholds are not met. The proposed approach was evaluated on a custom dataset comprising 53 public service intents, spanning formal and informal Indonesian language use. Experimental results demonstrate that the hybrid architecture achieves an intent classification accuracy of 86.8%, outperforming single-model approaches while maintaining an acceptable response time for practical deployment, particularly in public service scenarios where accuracy and reliability are prioritized over response speed. Furthermore, integrating a continuous learning mechanism enables the system to adapt to low-confidence queries over time, thereby improving robustness in real-world applications. These findings indicate that hybrid NLP architectures with confidence-aware decision mechanisms offer a practical and scalable solution for intelligent public service chatbots.
Downloads
References
A. Gr, “The impact of chatbots on public service provision : A qualitative interview study with citizens and public service providers,” vol. 41, no. February, 2024, doi: 10.1016/j.giq.2024.101927.
X. Li and J. Wang, “Should government chatbots behave like civil servants ? The effect of chatbot identity characteristics on citizen experience,” Gov. Inf. Q., vol. 41, no. 3, p. 101957, 2024, doi: 10.1016/j.giq.2024.101957.
A. M. Al-ansi, A. Garad, M. Jaboob, and A. Al-ansi, “Heliyon Elevating e-government : Unleashing the power of AI and IoT for enhanced public services,” Heliyon, vol. 10, no. 23, p. e40591, 2024, doi: 10.1016/j.heliyon.2024.e40591.
G. Papageorgiou, V. Sarlis, and M. Maragoudakis, “Enhancing E-Government Services through State-of-the-Art , Modular , and Reproducible Architecture over Large Language Models,” 2024, doi: https://doi.org/10.3390/app14188259.
A. R. Y. S. Prihatmanto and R. Andrian, “Transforming Public Services : A Systematic Review of Smart Government Frameworks , Architectures , and Implementation Challenges,” IEEE Access, vol. 12, no. September, pp. 135799–135810, 2024, doi: 10.1109/ACCESS.2024.3450907.
S. Hemesath and M. Tepe, “Public value positions and design preferences toward AI-based chatbots in e-government . Evidence from a conjoint experiment with citizens and municipal front desk officers,” Gov. Inf. Q., vol. 41, no. 4, p. 101985, 2024, doi: 10.1016/j.giq.2024.101985.
M. H. Miraz, A. Ya, S. Adeyinka-ojo, and J. B. Sarkar, “Intention to use determinants of AI chatbots to improve customer relationship management efficiency,” Cogent Bus. Manag., vol. 11, no. 1, p., 2024, doi: 10.1080/23311975.2024.2411445.
R. Santosa, A. B. Nusantara, and S. Imron, “Comparative Analysis of SVM and IndoBERT for Intent Classification in Indonesian Overtime Chatbots,” vol. 6, no. 3, pp. 258–270, 2025, doi: DOI:10.61628/jsce.v6i3.2058.
C. Ouaddi, L. Benaddi, A. Jakimi, A. Chehri, and R. Saadane, “ScienceDirect ScienceDirect Assessing Machine Learning Models for Enhancing Intent and Chatbots Detection in Tourism Assessing Machine Learning Models for Enhancing Intent Detection in Tourism Chatbots,” Procedia Comput. Sci., vol. 270, pp. 3162–3171, 2025, doi: 10.1016/j.procs.2025.09.441.
R. Aulia and A. Purnama, “Development of an Intent-Classification Chatbot to Support Operational Services at Kadin Indonesia,” vol. 5, no. 2, pp. 1171–1180, 2025, doi: https://doi.org/10.47709/brilliance.v5i2.7438.
Y. Zhang and R. Y. K. Lau, “Uncertainty Detection : A Multi ‑ View Decision Boundary Approach Against Healthcare Unknown Intents,” pp. 1–17, 2025, doi: https://doi.org/10.3390/app15137114.
I. Dube, “Chatbots: a tool to improve public service delivery and create public value,” vol. 9, no. 3, pp. 43–64, 2024, doi: https://doi.org/10.55190/JPADA.2024.341.
M. Saleem and J. Kim, “Intent aware data augmentation by leveraging generative AI for stress detection in social media texts,” 2024, doi: 10.7717/peerj-cs.2156.
A. Skuridin and M. Wynn, “Chatbot Design and Implementation : Towards an Operational Model for Chatbots,” 2024, doi: https://doi.org/10.3390/info15040226.
S. Senadheera et al., “Understanding Chatbot Adoption in Local Governments : A Review and Framework Understanding Chatbot Adoption in Local Governments :,” J. Urban Technol., vol. 32, no. 3, pp. 35–69, 2025, doi: 10.1080/10630732.2023.2297665.
C. Yu, J. Yan, and N. Cai, “ChatGPT in higher education : factors influencing ChatGPT user satisfaction and continued use intention,” no. May, pp. 1–11, 2024, doi: 10.3389/feduc.2024.1354929.
U. Informatics, D. Li, S. Wang, B. Zhao, Z. Ma, and L. Li, “A novel model based on a transformer for intent detection and slot filling,” Urban Informatics, 2024, doi: 10.1007/s44212-024-00056-6.
W. Christian et al., “Leveraging Leveraging IndoBERT IndoBERT and and DistilBERT DistilBERT for for Indonesian Indonesian emotion emotion Leveraging IndoBERT and DistilBERT for Indonesian classification in reviews classification in e-commerce reviews emotion classification in e-commerce reviews ScienceDirect,” Procedia Comput. Sci., vol. 269, pp. 321–330, 2025, doi: 10.1016/j.procs.2025.08.284.
S. Shreyashree, P. Sunagar, S. Rajarajeswari, and A. Kanavalli, “BERT-Based Hybrid RNN Model for Multi-class Text Classification to Study the Effect of Pre-trained Word Embeddings,” vol. 13, no. 9, pp. 667–675, 2022, doi: DOI:10.14569/IJACSA.2022.0130979.
J. Bae and S. Bum, “Accuracy-informed label smoothing and logit scaling for deep neural network calibration,” Appl. Soft Comput., vol. 188, no. November 2025, p. 114410, 2026, doi: 10.1016/j.asoc.2025.114410.
D. Lopez-paz and M. A. Ranzato, “Gradient Episodic Memory for Continual Learning,” no. Nips, 2022, doi: https://doi.org/10.48550/arXiv.1706.08840.
N. Brunswick and U. States, “Continual Learning of Large Language Models : A Comprehensive Survey Continual Learning of Large Language Models : A Comprehensive Survey,” vol. 58, no. 5, 2026, doi: 10.1145/3735633.
Z. Ke and B. Liu, “Continual Learning of Natural Language Processing Tasks: A Survey,” vol. 2, 2023, doi: https://doi.org/10.48550/arXiv.2211.12701.
M. Jbene, G. Jeon, A. Chehri, and R. Saadane, “Intent detection for task-oriented conversational agents : A comparative study of recurrent neural networks and transformer models,” no. June 2024, pp. 1–20, 2025, doi: 10.1111/exsy.13712.
A. Souha, C. Ouaddi, L. Benaddi, and A. Jakimi, “Pre-Trained Models for Intent Classification in Chatbot : Comparative Study and Critical Analysis,” 2023 6th Int. Conf. Adv. Commun. Technol. Netw., pp. 1–6, 2023, doi: 10.1109/CommNet60167.2023.10365312.
A. Tyagi, “Benchmark Text Preprocessing Techniques in Natural Language Processing,” 2024 4th Int. Conf. Innov. Sustain. Comput. Technol., pp. 1–6, 2024, doi: 10.1109/CISCT62494.2024.11134188.
R. A. Khachfeh, “An Enhanced Hybrid BERT-BiLSTM Learning Model for Arabic News Classification,” 2025 Int. Conf. Mach. Intell. Smart Innov., pp. 201–206, 2025, doi: 10.1109/ICMISI65108.2025.11115581.
H. Kyeremateng-boateng, “Choosing LS-Stat Confidence Scores for Neural Networks Predictions,” 2024 Int. Conf. E-mobility, Power Control Smart Syst., pp. 1–6, 2024, doi: 10.1109/ICEMPS60684.2024.10559353.
M. Hossain, S. Hossain, M. Safran, S. Alfarhood, M. Alfarhood, and M. F. Mridha, “A Hybrid Attention-Based Transformer Model for Arabic News Classification Using Text Embedding and Deep Learning,” IEEE Access, vol. 12, no. December, pp. 198046–198066, 2024, doi: 10.1109/ACCESS.2024.3522061.
H. Zhang and M. O. Shafiq, “Survey of transformers and towards ensemble learning using transformers for natural language processing,” J. Big Data, 2024, doi: 10.1186/s40537-023-00842-0.
M. Arevalillo-herráez, R. S. A. Luise, and Y. Wu, “Neurocomputing A non-deteriorating approach to improve Natural Language Understanding in Conversational Agents,” vol. 630, no. February, 2025, doi: https://doi.org/10.1016/j.neucom.2025.129652.
B. R. K, B. E. Babu, S. P. Racharla, P. Pavani, Y. Balagoni, and M. Ajmeera, “A Performance Evaluation of Transformer Models and Recurrent Neural Networks Models in Efficient Text Classification Tasks,” 2025 8th Int. Conf. Comput. Methodol. Commun., pp. 1171–1177, 2025, doi: 10.1109/ICCMC65190.2025.11140627.
W. Hybrid and C. Architecture, “Arsitektur Chatbot WhatsApp Hibrida Rasa - DeepSeek : Desain dan Evaluasi Performa Performance Evaluation,” vol. 15, pp. 446–454, 2026.
T. Papadopoulos and C. Alexopoulos, “Evaluating chatbot architectures for public service delivery : balancing functionality , safety , ethics , and adaptability,” no. October, 2025, doi: 10.3389/fpos.2025.1601440.
M. Abbasi, F. Cardoso, and P. Martins, “Comparative Performance Analysis of Large Language Models for Structured Data Processing : An Evaluation Framework Applied to Bibliometric Analysis,” pp. 1–30, 2026, doi: https://doi.org/10.3390/app16020669.
L. Zhang, S. Wang, F. Yuan, B. Geng, and M. Yang, “Lifelong language learning with adaptive uncertainty regularization,” Inf. Sci. (Ny)., vol. 622, pp. 794–807, 2023, doi: 10.1016/j.ins.2022.11.141.
M. N. Budiyanto and A. Syafebri, “Artificial Intelligence in Public Administration : A Systematic Literature Review on Opportunities and Ethical Challenges,” pp. 244–257, 2025, doi: 10.18502/kss.v10i30.20347.
Additional Files
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Barka Satya, Mei Parwanto Kurniawan, Toto Indryatmoko, As'adurrofiq
This work is licensed under a Creative Commons Attribution 4.0 International License.
