Primary supervisor

Kla Tantithamthavorn

🎯 Research Motivation

While many AI-powered coding assistants (e.g., GitHub Copilot, ChatGPT Code Interpreter) improve coding productivity, they are not optimized for pedagogical impact. CS students need not just code completion but understanding, feedback, and guidance that nurtures problem-solving and conceptual mastery.

Your research could bridge this gap by designing an AI IDE extension that acts as a mentor, dynamically adapting its feedback to the learner’s skill level, learning style, and progress.

đź’ˇ Core Research Idea

Design and evaluate an intelligent IDE extension that integrates adaptive learning models with software engineering intelligence to support CS students in real-time.

Key Functionalities:

  1. Adaptive Scaffolding:

    • Detect when a student is struggling and suggest next steps rather than full solutions.

    • Provide hints tailored to the student’s coding history and cognitive load.

  2. Concept Awareness Engine:

    • Recognize which computer science concepts (e.g., recursion, data structures, design patterns) the code engages.

    • Deliver micro-tutorials, concept visualizations, or quizzes in the IDE contextually.

  3. Code Reflection Prompts:

    • After solving a task, the AI asks reflective questions (“Why does this algorithm have O(n²) complexity?”) to reinforce conceptual learning.

  4. Ethical AI Coach:

    • Encourage responsible AI use by making students co-thinkers, not code copiers.

    • Offer transparency in reasoning (“This suggestion is based on your prior function definitions and problem context.”)

  5. Learning Analytics Dashboard:

    • Visualize coding progress, error types, and conceptual mastery over time.

    • Integrate with LMSs (e.g., Moodle, Canvas) for instructor dashboards.

🔍 Potential Research Questions

  • How can we model student learning states from IDE interaction data and code traces?

  • To what extent can AI-based scaffolding improve conceptual understanding compared to traditional static hints?

  • How do students perceive trust, autonomy, and overreliance on AI in an educational coding context?

  • What are the ethical and pedagogical trade-offs of AI feedback versus human tutor feedback?