The Role of Natural Language Processing in Enhancing Chatbot Effectiveness for E-Government Services
DOI:
https://doi.org/10.33050/corisinta.v2i1.71Keywords:
Natural Language Processing (NLP), E-Government Chatbots, Public Service Automation, AI Ethics, Multilingual NLPAbstract
The rapid digital transformation of public administration has led to the adoption of (B) Natural Language Processing (NLP)-powered chatbots to enhance the accessibility, efficiency, and responsiveness of (O) e-government services. However, despite their increasing deployment, many government chatbots still struggle with intent recognition, response accuracy, multilingual processing, and user engagement, limiting their effectiveness. This study investigates (M) the role of NLP in improving chatbot performance within e-government services by evaluating four case studies: Ask Jamie (Singapore), UK Government Digital Assistant, MyGov Corona Helpdesk (India), and Gov.sg Chatbot. Using a mixed-methods approach, this research assesses chatbot effectiveness based on accuracy, response time, query resolution rate, and user satisfaction metrics. The findings indicate that (R) NLP-driven chatbots significantly outperform rule-based systems, with higher accuracy (up to 89%), faster response times (~2.1 seconds), and improved query resolution rates (92%), demonstrating their capacity to automate public service delivery efficiently. However, key challenges remain, including bias in NLP models, data privacy concerns, and the difficulty of integrating NLP chatbots into legacy IT infrastructures. Additionally, multilingual processing remains a limitation, affecting inclusivity for diverse populations. To overcome these challenges, this study proposes advancements in adaptive NLP models, real-time learning algorithms, ethical AI frameworks, and blockchain-based security solutions to ensure fair, secure, and transparent chatbot interactions in digital governance. These findings contribute to the growing body of research on AI-driven public service automation and highlight the potential of NLP to enhance (C) citizen-government interactions, reduce administrative burdens, and improve trust in e-government platforms. Future research should focus on bias mitigation, improving multilingual NLP capabilities, and integrating AI ethics into chatbot governance frameworks to ensure sustainable, scalable, and citizen-centric e-government chatbot solutions.
References
S. Ruder, Transfer Learning for Natural Language Processing. O’Reilly Media, 2021.
J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, BERT: Pre-training of Deep Bidirectional Transform-
ers for Language Understanding. Proceedings of NAACL, 2021.
Y. Shen, P. R. S. Kumar, and S. Zhang, Advances in Deep Learning for Natural Language Processing.
Elsevier, 2021.
D. S. S. Wuisan, R. A. Sunardjo, Q. Aini, N. A. Yusuf, and U. Rahardja, “Integrating artificial intelligence
in human resource management: A smartpls approach for entrepreneurial success,” Aptisi Transactions
on Technopreneurship (ATT), vol. 5, no. 3, pp. 334–345, 2023.
A. Vaswani et al., “Attention is all you need,” in Proc. Neural Information Processing Systems (NeurIPS),
, pp. 1–12.
K. L. J. Devlin, M. Chang and K. Toutanova, “Bert: Pre-training of deep bidirectional transformers for
language understanding,” Journal of Computational Linguistics, vol. 48, no. 2, pp. 4171–4186, 2022.
T. Wolf et al., “Transformers: State-of-the-art natural language processing,” Journal of Artificial Intelli-
gence Research, vol. 55, pp. 38–45, 2022.
R. K. Gupta and A. R. Joshi, “Conversational ai for government chatbots: An nlp perspective,” in Proc.
IEEE Int. Conf. on Artificial Intelligence (ICAI), 2021, pp. 115–122.
T. Ayuninggati, N. Lutfiani, and S. Millah, “Crm-based e-business design (customer relationship man-
agement) case study: Shoe washing service company s-neat-kers,” International Journal of Cyber and IT
Service Management, vol. 1, no. 2, pp. 216–225, 2021.
H. Zhang et al., “Multilingual nlp for government chatbots: Challenges and opportunities,” IEEE Access,
vol. 9, pp. 117 345–117 360, 2021.
R. Ferrara, “Ethics and bias in ai chatbots for e-government services,” in Proc. IEEE Int. Conf. on Ethics
in AI (ICAI Ethics), 2021, pp. 65–72.
M. Loukides, AI-Powered Chatbots in Public Services: A Deep Learning Approach. O’Reilly Media,
X. Liu, Y. Wu, and H. Zhang, “Transformer-based conversational ai in public administration,” in Proc.
IEEE Int. Conf. on Computational Intelligence and AI Applications, 2022, pp. 89–96.
C. D. Manning, “Part-of-speech tagging from 1990 to the present: A comparative analysis,” Computa-
tional Linguistics, vol. 42, no. 3, pp. 687–723, 2022.
L. H. A. P. Prawira, A. F. Ummah, M. R. Aditiya, and D. W. Nugroho, “Knowledge management: Efforts
to create an excellent digital creative industry,” Startupreneur Business Digital (SABDA Journal), vol. 2,
no. 2, pp. 172–181, 2023.
H. Zhang, “Improving named entity recognition for government chatbots using bert,” in Proc. 2022 IEEE
Int. Conf. on NLP and Speech Processing, 2022, pp. 150–157.
T. Williams, “Ensuring data privacy in nlp-based government chatbots,” IEEE Security & Privacy, vol. 19,
no. 5, pp. 48–55, 2022.
Y. Bengio and G. Hinton, “Deep learning for nlp: Trends and challenges,” IEEE Transactions on Artificial
Intelligence, vol. 5, no. 3, pp. 120–128, 2023.
A. Radford et al., “Learning transferable visual models from natural language supervision,” IEEE Trans-
actions on Computer Vision, vol. 12, no. 6, pp. 8748–8757, 2023.
P. Schmidt and K. Tanaka, “Bias detection in nlp models for government chatbots,” AI Ethics, vol. 8,
no. 4, pp. 341–356, 2023.
F. Kruger, Z. Queen, O. Radelva, and N. Lawrence, “Comparative analysis of scientific approaches in
computer science: A quantitative study,” International Transactions on Education Technology (ITEE),
vol. 2, no. 2, pp. 120–128, 2024.
T. Nguyen and L. Roberts, “Speech-to-text nlp for enhancing chatbot usability in public services,” in Proc.
IEEE Conf. on Human-Computer Interaction (HCI), 2023, pp. 102–109.
M. Gomez and C. Wilson, “Blockchain for secure ai chatbots in e-government services,” IEEE Transac-
tions on Blockchain, vol. 6, no. 1, pp. 59–72, 2024.
K. Choi and H. Park, “Adaptive nlp models for real-time government chatbots,” AI and Society, vol. 39,
pp. 1–18, 2024.
A. Thomas and R. Patel, “Chatbot efficiency in e-government: A case study of ai integration,” Journal of
Digital Governance, vol. 16, no. 2, pp. 102–119, 2024.
L. Wei and J. Kim, “Trust and transparency in nlp chatbots for government services,” in Proc. IEEE Conf.
on Digital Transformation, 2024, pp. 76–84.
J. D. Gates, Y. Yulianti, and G. A. Pangilinan, “Big data analytics for predictive insights in healthcare,”
International Transactions on Artificial Intelligence, vol. 3, no. 1, pp. 54–63, 2024.
R. Fernandez and M. Singh, “Ensuring inclusivity in multilingual chatbots for e-government,” Computers
in Society, vol. 31, pp. 45–62, 2024.
J. Martin and T. Williams, “Ethical considerations in nlp-based government chatbots,” AI Society, vol. 38,
pp. 187–203, 2023.
A. Sharma and P. Gupta, “Mitigating algorithmic bias in nlp-based chatbots for e-government services,”
Journal of Artificial Intelligence Ethics, vol. 12, no. 3, pp. 55–70, 2024.
A. Ghosal, S. Kumar, and U. Ratan, Transformers for Natural Language Processing. Springer, 2021.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Mungkap Mangapul Siahaan, Richard Andre Sunarjo, Rizky Sebastian, Syahrul Muarif Wahid (Authors)
This work is licensed under a Creative Commons Attribution 4.0 International License.
