INTELLIGENT TUTORING SYSTEMS IN THE EDUCATIONAL PROCESS FOR THE TRAINING OF FUTURE IT-SPECIALISTS
DOI:
https://doi.org/10.31110/2616-650X-vol14i2-011Keywords:
intelligent tutor system, ChatGPT, programming, Elixir, IT‑specialist training, personalized training, pedagogical informatics, adaptive technologiesAbstract
The article offers a theoretically grounded methodological basis for implementing intelligent tutoring systems (ITS) in the training of future IT specialists, leveraging generative language models, thereby addressing the gap identified in the literature between traditional programming training methods and modern IT market requirements. Against the background of the rapid evolution of programming languages and the high dropout rate in introductory courses of 30% to 50%, the author systematizes the ITS architecture (domain, student, tutor models, and interface) and theoretically justifies how the combination of the conversational model with diagnostic algorithms has the potential to provide adaptive learning trajectories and operational feedback. Key novelty – conceptual model guidance-practice-transformation (G-P-T), which offers structuring of the learning process through three stages from explanatory hints to independent projects and transfer of knowledge to new contexts, which is developed on the basis of the synthesis of theories of constructivism, andragogy, and cognitive load. Analysis of meta-analytical studies shows that classical ITS provides a success gain of about 0.61–0.80 standard deviations, and the use of modern language models shows an even higher effect of about 0.867. A comparison of disciplines reveals the greatest potential in programming due to the ability to generate and verify code, but a literature review identifies limitations: false answers, reduced autonomy, and risks of academic dishonesty. Practical contribution — conceptual framework of implementation: design of domain knowledge bases for Elixir, Python, and Java; level-diagnostic algorithms; G-P-T scenarios for three modules; rules for double verification of answers according to official documentation; mechanisms of ethical control; requirements for digital literacy of teachers and students; localization guidelines for the Ukrainian context. The consistency of the approach with constructivism, andragogy, and cognitive load theory is substantiated: the system has the potential to optimize information, activate previous knowledge, provide hints only when necessary, and gradually reduce support. Areas of further research are outlined: empirical verification of the proposed model; Ukrainian-language corpora and glossaries; comparison across disciplines (algorithms, DevOps, cybersecurity); automatic verification of answers; and countermeasures against false answers. The article offers a theoretically grounded, practical framework that has the potential to improve educational outcomes, reduce dropouts, and promote a culture of academic integrity in IT education in Ukraine.
References
Теоретичні основи і механізми взаємодії вищої освіти та ринку праці в умовах воєнного стану та післявоєнного відновлення України / Ю. Скиба та ін. 2024. С. 43–48. URL: https://ihed.org.ua/wp-content/uploads/2025/03/Vzayemodiya-VO-ta-rynku-pratsi_IVO-2024-135p.pdf
AI tutoring outperforms in-class active learning: an RCT introducing a novel research-based design in an authentic educational setting / G. Kestin та ін. Scientific Reports. 2025. Т. 15, № 1. https://doi.org/10.1038/s41598-025-97652-6
Andragogy in Practice: Applying a Theoretical Framework to Team Science Training in Biomedical Research / J. M. Knapke та ін. British Journal of Biomedical Science. 2024. Т. 81. https://doi.org/10.3389/bjbs.2024.12651
Are Graduates Digitally Unprepared?–A Digital Technology Gap Analysis From Alumni and Employer's Perspectives / X. Zhou та ін. Journal of Computer Assisted Learning. 2025. Т. 41, № 4. https://doi.org/10.1111/jcal.70046
A systematic review of AI-driven intelligent tutoring systems (ITS) in K-12 education / A. Létourneau та ін. npj Science of Learning. 2025. Т. 10, № 1. https://doi.org/10.1038/s41539-025-00320-7
Blended learning: the new normal and emerging technologies / C. Dziuban та ін. International Journal of Educational Technology in Higher Education. 2018. Т. 15, № 1. https://doi.org/10.1186/s41239-017-0087-5
Blyth W. A. L., Bloom B. S., Krathwohl D. R. Taxonomy of Educational Objectives. Handbook I: Cognitive Domain. British Journal of Educational Studies. 1966. Т. 14, № 3. P. 119. https://doi.org/10.2307/3119730
Bringula R. ChatGPT in a programming course: benefits and limitations. Frontiers in Education. 2024. Т. 9. https://doi.org/10.3389/feduc.2024.1248705
Enhancing Programming Performance, Learning Interest, and Self-Efficacy: The Role of Large Language Models in Middle School Education / B. Tang та ін. Systems. 2025. Т. 13, № 7. P. 555. https://doi.org/10.3390/systems13070555
Ericsson K. A., Krampe R. T., Tesch-Römer C. The role of deliberate practice in the acquisition of expert performance. Psychological Review. 1993. Т. 100, № 3. P. 363–406. https://doi.org/10.1037/0033-295x.100.3.363
Güner H., Er E. AI in the classroom: Exploring students’ interaction with ChatGPT in programming learning. Education and Information Technologies. 2025. https://doi.org/10.1007/s10639-025-13337-7
Kolb D. A. Experiential Learning: Experience as the Source of Learning and Development. FT Press, 1983. 288 p.
Kulik C.-L. C., Kulik J. A. Effectiveness of computer-based instruction: An updated analysis. Computers in Human Behavior. 1991. Т. 7, № 1-2. P. 75–94. https://doi.org/10.1016/0747-5632(91)90030-5
Kulik J. A., Fletcher J. D. Effectiveness of Intelligent Tutoring Systems. Review of Educational Research. 2016. Т. 86, № 1. P. 42–78. https://doi.org/10.3102/0034654315581420
Learning Analytics for Bridging the Skills Gap: A Data-Driven Study of Undergraduate Aspirations and Skills Awareness for Career Preparedness / J. W. Lai та ін. Education Sciences. 2025. Т. 15, № 1. P. 40. https://doi.org/10.3390/educsci15010040
Margulieux L. E., Morrison B. B., Decker A. Reducing withdrawal and failure rates in introductory programming with subgoal labeled worked examples. International Journal of STEM Education. 2020. Т. 7, № 1. https://doi.org/10.1186/s40594-020-00222-7
Mezirow J. Transformative Learning: Theory to Practice. New Directions for Adult and Continuing Education. 1997. Т. 1997, № 74. P. 5–12. https://doi.org/10.1002/ace.7401
Parr C. Not Staying the Course. Inside Higher Ed. URL: https://www.insidehighered.com/news/2013/05/10/new-study-low-mooc-completion-rates#:~:text=The%20course%20with%20the%20highest,who%20enrolled%20completed%20the%20course
Smith C. Bridging the Digital Skills Gap with a Focused Student Initiative. Pedagogy: The LTEC Learning and Teaching Showcase. 2025. Т. 1, № 1. https://doi.org/10.57898/pedagogy.267
Sweller J. Cognitive load theory, learning difficulty, and instructional design. Learning and Instruction. 1994. Т. 4, № 4. P. 295–312. https://doi.org/10.1016/0959-4752(94)90003-5
The global digital skills gap: Current trends and future directions. RAND Corporation, 2021. https://doi.org/10.7249/rra1533-1
The Impact of Adaptive Learning Technologies, Personalized Feedback, and Interactive AI Tools on Student Engagement: The Moderating Role of Digital Literacy / H. Yaseen та ін. Sustainability. 2025. Т. 17, № 3. P. 1133. https://doi.org/10.3390/su17031133
Wang J., Fan W. The effect of ChatGPT on students’ learning performance, learning perception, and higher-order thinking: insights from a meta-analysis. Humanities and Social Sciences Communications. 2025. Т. 12, № 1. https://doi.org/10.1057/s41599-025-04787-y
Zimmerman B. J. Self-Regulated Learning: Theories, Measures, and Outcomes. International Encyclopedia of the Social & Behavioral Sciences. 2015. P. 541–546. https://doi.org/10.1016/b978-0-08-097086-8.26060-1
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Сергій Мельник
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
- Authors grant the journal a right of the first publication of the work under a Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC 4.0)that allows others freely to use (read, copy and print) submissions, search content and link to published articles, disseminate their full text and use them for any legitimate non-commercial purposes (i.e. educational or scientific) with the mandatory reference to the article’s authors and initial publication in this journal.
- Original published articles cannot be used by users (exept authors) for commercial purposes or distributed by third-party intermediary organizations for a fee.
