AI-POWERED PERSONALIZED LEARNING ASSISTANT FOR FRONTEND DEVELOPMENT EDUCATION
Keywords:
Frontend Education, React, AI Assistant, Personalized Learning, Debugging, Component ArchitectureAbstract
This article investigates an AI-powered personalized learning assistant model designed for students studying frontend development (HTML, CSS, JavaScript, React) at higher education institutions in Uzbekistan. The relevance of the study stems from the fact that students face considerable difficulty in independently identifying syntactic, logical, and asynchronous errors in their code, as well as errors related to responsive design and the prop/state relationships between React components, which reduces the overall effectiveness of practical learning. To address this problem, the article proposes an “AI Assistant” system that analyzes student code in real time and, instead of providing a ready-made solution, offers personalized, step-by-step guidance on how to correct the identified error. The study describes the system’s four-layer architecture, a three-stage experimental process, and a set of performance indicators. The expected results indicate that the proposed model reduces debugging time, increases independent error-correction ability, and deepens students’ understanding of component-based architecture.References
1. Park, T., Wiedenbeck, S. (2011). Learning web development: Challenges at an earlier stage of computing education. Proceedings of the Seventh International Workshop on Computing Education Research (ICER '11), ACM. https://dl.acm.org/doi/10.1145/2016911.2016937
2. Park, T., Wiedenbeck, S. (2011). Learning web development: Challenges at an earlier stage of computing education (PDF version). ResearchGate. https://www.researchgate.net/publication/221209607_Learning_web_development_Challenges_at_an_earlier_stage_of_computing_education
3. Park, T., Dorn, B., Forte, A. (2015). An Analysis of HTML and CSS Syntax Errors in a Web Development Course. ACM Transactions on Computing Education, 15(1), 1–21. https://dl.acm.org/doi/10.1145/2700510
4. A Case for Learning Functional Components First: Teaching Students Props and State in React. Codementor. https://www.codementor.io/@alyssahope/a-case-for-learning-functional-components-first-njix8bc9t
5. How to Learn the Hard Parts of React — and Tips to Conquer Them. freeCodeCamp, 2024. https://www.freecodecamp.org/news/hard-parts-of-react/
6. Majdoub, Y. et al. (2024). Debugging with Open-Source Large Language Models: An Evaluation. Proceedings of the 18th ACM/IEEE International Symposium on Empirical Software Engineering and Measurement (ESEM '24). arXiv preprint. https://arxiv.org/html/2409.03031v1
7. Chen, X., Lin, M. et al. (2023). Teaching Large Language Models to Self-Debug. arXiv preprint arXiv:2304.05128. https://arxiv.org/abs/2304.05128
8. Kang, S. et al. (2024). Explainable Automated Debugging via Large Language Model-Driven Scientific Debugging (AutoSD). Empirical Software Engineering, Springer. https://link.springer.com/article/10.1007/s10664-024-10594-x
9. Closing the Loop: An Instructor-in-the-Loop AI Assistance System for Supporting Student Help-Seeking in Programming Education. arXiv preprint, 2025. https://arxiv.org/pdf/2510.14457
10. CodeExemplar: Example-Based Scaffolding for Introductory Programming in the GenAI Era. arXiv preprint, 2026. https://arxiv.org/pdf/2603.23830
11. MazeMate: An LLM-Powered Chatbot to Support Computational Thinking in Gamified Programming Learning. arXiv preprint, 2025. https://arxiv.org/pdf/2511.03727
12. Uzbekistan's strategy for the development of artificial intelligence technologies until 2030. Digital Watch Observatory, 2025. https://dig.watch/resource/uzbekinstans-strategy-for-the-development-of-artificial-intelligence-technologies-until-2030
13. The Future of Higher Education in Uzbekistan: The Potential and Challenges of Integrating Artificial Intelligence (National Survey). Perspectives of Higher Education Development, 2025. https://erasmus.uz/journal/index.php/files/article/view/129
14. Generative AI Governance in Distance Higher Education: Aligning Uzbekistan's Digital Learning Methodology with International Standards. 2026. https://www.pstjournal.uz/index.php/pst/article/view/125
15. Scaffolding Metacognition in Programming Education: Understanding Student-AI Interactions and Design Implications. arXiv preprint, 2025.