[TAKEN] AI Code Generators for Novice Programmers (2)

This project would be appropriate for Year 4, Year 5 or MSc student.

AI Coding Assistants (e.g. GitHub Copilot) are quickly becoming a valuable tool for developers. Whether these tools should be used by novice student programmers taking introductory programming courses is an important question. Several studies have begun to explore the effect of the use of coding assistants when used by novice programmers. One such study by Kazemitabaar et al. [1] suggests several ways that an AI coding assistant might be adapted for use by novice programmers, including:

  1. breaking code suggestions into smaller pieces that are presented sequentially in a logical sequence [TAKEN]
  2. requiring the student to complete a small, contextualised exercise before the suggestion is made available [TAKEN]

Two projects are available on this theme, each exploring one of the above adaptations of AI coding assistants for use by novice programmers. Furthermore, if you have your own idea for adapting an AI coding assistant for novice programmers, please email me.

The context for these projects can be any programming language that is commonly used in introductory programming courses (e.g. Python, Java, C). Students undertaking these projects will be free to use the programming languages that they deem most appropriate.

[1] M. Kazemitabaar, J. Chow, C. K. T. Ma, B. J. Ericson, D. Weintrop, and T. Grossman, ‘Studying the effect of AI Code Generators on Supporting Novice Learners in Introductory Programming’, in Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems, Hamburg Germany: ACM, Apr. 2023, pp. 1–23. doi: 10.1145/3544548.3580919.