Design of an AI-Driven Intelligent Teaching Model for Programming Education in Higher Education
Year: 2026
Type: conference-paper
Abstract: Artificial intelligence is reshaping programming education by enabling adaptive learning support, automated error diagnosis, and data-driven instructional decision-making. Nevertheless, most existing AI applications in this field remain technology-centric, lacking close alignment with pedagogical design principles, disciplinary learning goals, and explicit application of specific computational algorithms. To mitigate this issue, this study proposes an AI-driven intelligent teaching model tailored to higher education programming education. Rooted in the AI-TPACK framework, SAMR model, scaffolding theory and learning analytics, the model integrates intelligent agent infrastructure (driven by LLM fine-tuning and syntax/semantic analysis algorithms), pedagogical coordination, instructional regulation (based on k-means clustering) and process-oriented feedback (supported by hybrid recommendation algorithm) into a cohesive instructional architecture. This paper elaborates on the model's structural components, core algorithms’ parameter settings and application scenarios, operational mechanisms across pre-class, in-class and post-class stages, and verifies its effectiveness through empirical research. The model provides a structured, interpretable and scalable algorithm-driven approach to optimize programming instruction, offering theoretical insights and practical references for AI-enhanced teaching models in higher education.
Authors: Miao He, Haslinda Sutan Ahmad Nawi
Language: English
Subfield: Computer Science Applications
Field: Computer Science
Domain: Physical Sciences
SDG: Quality education
Open Access status: hybrid
OpenAlex ID: W7213263460
