Leveraging Large Language Models for Analysis of Student Course Feedback

Abstract

This study investigates the use of large language models, specifically ChatGPT, to analyse the feedback from a Summative Evaluation Tool (SET) used to collect student feedback on the quality of teaching. We find that these models enhance comprehension of SET scores and the impact of context on student evaluations. This work aims to reveal hidden patterns in student evaluation data, demonstrating a positive first step towards automated, detailed analysis of student feedback.