Development of an Intelligent Educational Chatbot Using NLP and Machine Learning
Keywords:
Educational chatbot, Natural Language Processing, Machine Learning, digital learning, artificial intelligenceAbstract
This study aims to develop an intelligent educational chatbot using Natural Language Processing (NLP) and Machine Learning (ML) to support independent student learning in English. As digital learning increasingly demands adaptive and responsive tools, chatbots offer the potential to provide real-time, personalized interactions. The chatbot in this research was designed with transformer-based NLP models and trained using supervised learning techniques. The development process followed the Borg & Gall Research and Development (R&D) model, including stages such as needs analysis, system design, prototyping, testing, and refinement. Through the integration of NLP and ML, the chatbot was expected to deliver natural dialogue, contextual understanding, and accurate educational feedback. Testing was conducted with 15 eleventh-grade high school students using pre- and post-tests. Results showed a significant improvement in learning outcomes, with average scores rising from 61.3 to 84.2. In addition to academic gains, students reported increased motivation, confidence, and comfort with self-directed learning. These findings confirm that the developed chatbot is effective not only in delivering knowledge but also in enhancing students' engagement and autonomy. The study concludes that the application of AI technologies, particularly NLP and ML, in education holds great potential as an inclusive, efficient, and scalable solution for the future of digital learning.
Downloads
References
Apriadi, E. A., & Bisri, M. (2025). Optimization of BPJS health facility distribution with K-Means clustering algorithm. International Journal of Technology and Computer Science, 1(1), 1–13.
Apriadi, E. A., Lestari, S., & Irianto, S. Y. (2024). Comparison of performance of K-Nearest Neighbors and Neural Network algorithm in Bitcoin price prediction. Sinkron: Jurnal dan Penelitian Teknik Informatika, 8(2), 617–622.
Armstrong, T. (2016). The power of the adolescent brain: Strategies for teaching middle and high school students. ASCD.
Chen, L., Chen, P., & Lin, Z. (2020). Artificial intelligence in education: A review. IEEE Access, 8, 75264–75278. https://doi.org/10.1109/ACCESS.2020.2988510
Creswell, J. W. (2012). Educational research: Planning, conducting, and evaluating quantitative and qualitative research (4th ed.). Pearson Education.
Dillenbourg, P. (2019). Orchestration graphs: Modeling scalable education. Educational Technology Research and Development, 67(2), 449–476. https://doi.org/10.1007/s11423-018-09656-z
Fryer, L. K., & Nakao, K. (2020). The promise of chatbot technology for education: A preliminary study. Journal of Educational Technology & Society, 23(4), 76–88.
Hussain, M., & Athar, A. (2021). Effectiveness of chatbots in education: A systematic review. International Journal of Advanced Computer Science and Applications (IJACSA), 12(5), 225–232. https://doi.org/10.14569/IJACSA.2021.0120528
Irianto, S. Y., Yulianto, R., Karnila, S., & Yuliawati, D. (2021). Studi Akurasi Karakteristik Retina sebagai Future Identification dengan Euclidean Distance Metrics. Informatika Mulawarman : Jurnal Ilmiah Ilmu Komputer, 16(1), 19. https://doi.org/10.30872/jim.v16i1.5136
Mayer, R. E., & Moreno, R. (2003). Nine ways to reduce cognitive load in multimedia learning. Educational Psychologist, 38(1), 43–52. https://doi.org/10.1207/S15326985EP3801_6
Nurhadi, N. (2017). Strategi pembelajaran multisensori untuk anak berkebutuhan khusus. Jakarta: Prenadamedia Group.
Pereira, A., Díaz, Ó., & García, R. (2019). Leveraging chatbots to improve self-guided learning through conversational quizzes. International Journal of Human–Computer Studies, 125, 41–54. https://doi.org/10.1016/j.ijhcs.2018.12.004
Prasetya, H. (2019). Analisis data kualitatif dalam penelitian tindakan kelas. Yogyakarta: Deepublish.
Roberts, J., White, D., & Wastiau, P. (2019). Technology-supported personalised learning: A review of research. European Journal of Education, 54(1), 29–45. https://doi.org/10.1111/ejed.12321
Rus-Vanide, T., & Atapattu, T. (2021). A review of intelligent tutoring systems using natural language processing. Computers & Education: Artificial Intelligence, 2, 100024. https://doi.org/10.1016/j.caeai.2021.100024
Shawar, B. A., & Atwell, E. (2007). Chatbots: Are they really useful? LDV Forum, 22(1), 29–49.
Smith, D. D., & Tyler, N. C. (2019). Introduction to special education: Making a difference (8th ed.). Pearson.
Suryanti, P., & Apriadi, E. A. (2025). Kecerdasan buatan dalam produksi konten jurnalistik: Analisis etika dan akurasi komunikasi berita berbasis AI. Journal Media Public Relations, 5(1), 253–263.
Suryanti, P., Apriadi, E. A., & Laras, H. D. (2024). Communication interaction in children with special needs: Descriptive study. Journal of Public Relations and Digital Communication (JPRDC), 2(2), 64–68.
Syaputra, A. E., Kristiawan, H., Nugroho, A. Y., Apriadi, E. A., Alamin, Z., Arisandi, D., Siswanto, L., Pramana, H. J., Jufri, M. T., & Chandra, N. A. (2025). Keamanan jaringan komputer. Sada Kurnia Pustaka.
Woolf, B. P. (2010). Building intelligent interactive tutors: Student-centered strategies for revolutionizing e-learning. Morgan Kaufmann.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Ribut Julianto, Tedi Gunawan, Eko Aziz Apriadi
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All articles published in the International Journal of Technology and Computer Science are licensed under the Creative Commons Attribution-ShareAlike License (CC BY-SA). This license allows others to share, adapt, and build upon the work, even for commercial purposes, as long as they credit the original creation and license their new creations under the identical terms.
By submitting and publishing with the International Journal of Technology and Computer Science, authors agree to the following terms:
Ownership and Copyright
Authors retain copyright and grant the journal the right to first publication. The work will be simultaneously licensed under the Creative Commons Attribution-ShareAlike License (CC BY-SA), ensuring continued free and open access to the research.
Attribution Requirements
When reusing or redistributing the published material, proper attribution must include:
- Citation of the original article.
- Mention of the journal name and publication date.
- A link to the published work and the license details.
ShareAlike Terms
Any derivative works based on the original must be distributed under the same license (CC BY-SA).
Open Access
The International Journal of Technology and Computer Science is dedicated to open access, providing free and unrestricted access to all published articles without subscription fees or other access barriers.
Author Warranties
By submitting the manuscript, authors warrant that:
- The work is original and has not been published elsewhere.
- All co-authors consent to publication.
- The work does not infringe on any copyright, trademark, or proprietary rights.
No Additional Restrictions
Authors and readers are not permitted to impose legal terms or technological measures that legally restrict others from doing anything the license permits.
