Enhancing Programming Learning with AI-Generated Contextual Examples in Digital Creativity

Scott, Michael ORCID logoORCID: https://orcid.org/0000-0002-6803-1490, Murturi, Sokol and Walton-Rivers, Joseph (2023) Enhancing Programming Learning with AI-Generated Contextual Examples in Digital Creativity. In: Proceedings of the SICSA Workshop on the Pedagogical Impacts of ChatGPT and Knowledge-Driven Large Language Models, August 24, 2023, Aberdeen, Scotland.

Enhancing Programming Learning with AI-Generated Contextual Examples in Digital Creativity.pdf - Published Version
Available under License Creative Commons Attribution.

Download (2MB) | Preview

Abstract / Summary

Programming concepts are challenging for new learners to grasp. This is especially the case for creative arts students who are typically unfamiliar with computing concepts and the associated vocabulary at enrolment. One means to enhance their learning is to situate examples in a relatable disciplinary context and to adapt learning material accordingly. However, this can be onerous and time-consuming to prepare; particularly in diverse modules that include learners from a wide range of different disciplines. This position paper proposes the use of large language models to automate tailoring the content of adaptive hypermedia systems such as personalised wikis. These tools can re-situate examples into many contexts that learners are already familiar with. A pilot study using ChatGPT (using GPT-4) for a first-stage undergraduate Digital Creativity module is presented. Generative artificial intelligence changes the examples used to illustrate programming concepts according to a student’s course. These examples are evaluated by academic colleagues drawn from the different course teams to rate the generated analogies. Initial results are encouraging, illustrating a high degree of face validity. Further work in 2023-24 will evaluate whether this improves learning during the module.

Item Type: Conference or Workshop Item (Lecture)
Subjects: Education
Courses by Department: The Games Academy > Digital Games
Depositing User: Michael Scott
Date Deposited: 24 Aug 2023 17:34
Last Modified: 24 Aug 2023 17:34
URI: https://repository.falmouth.ac.uk/id/eprint/5064


View Item View Item (login required)