Primary supervisor

Ee Hui Lim

Generative AI is increasingly being used to support feedback and reflection in education. However, most current tools rely on cloud-based models, raising concerns around privacy, data governance, and trust, especially when handling sensitive student teamwork data.

This project explores the use of locally deployed generative AI (GenAI) to support teamwork feedback in computing education contexts. The focus is not only on technical feasibility, but also on how students and educators perceive, trust, and interact with AI-generated feedback when it is processed locally.

The project will investigate how locally hosted AI models can be used to generate summaries, feedback suggestions, or insights from teamwork data (e.g., reflections, check-ins), while preserving privacy and transparency.

Aim/outline

The project aims to explore how local GenAI can be used to support teamwork feedback in a privacy-aware and pedagogically meaningful way.

Specifically, the project will:

  • Set up a local GenAI environment (e.g., lightweight LLM or open-source model)
  • Explore use cases such as:
    • summarising teamwork reflections
    • generating formative feedback suggestions
    • identifying collaboration patterns
  • Conduct small-scale user studies with students and/or educators to evaluate:
    • perceived usefulness
    • trust and transparency
    • concerns around privacy
  • Compare perceptions of local vs cloud-based AI feedback (if feasible)
  • Derive design and ethical considerations for using GenAI in teamwork analytics

Required knowledge

Interest in AI, learning analytics, or computing education. Familiarity with Python and working with AI tools is desirable.