iReflect: Enhancing Reflective Learning with LLMs: A Study on Automated Feedback in Project Based Courses

Bhojan Anand, Quek Sze Long

2025

Abstract

Reflective learning in education offers various benefits, including a deeper understanding of concepts, increased self-awareness, and higher-quality project work. However, integrating reflective learning into the syllabus presents challenges, such as the difficulty of grading and the manual effort required to provide in-dividualised feedback. In this paper, we explore the use of Large Language Models (LLMs) to automate formative feedback on student reflections. Our study is conducted in the CS4350 Game Development Project course, where students work in teams to develop a game through multiple milestone assessments over the semester. As part of the reflective learning process, students write reflections at the end of each milestone to prepare for the next. Students are given the option to use our automated feedback tool to improve their submissions. These reflections are graded by Teaching Assistants (TAs). We analyse the impact of the tool by comparing students’ initial reflection drafts with their final submissions and surveying them on their experience with automated feedback. In addition, we assess students’ perceptions of the usefulness of reflective writing in the game development process. Our findings indicate that students who revised their reflections after using the tool showed an improvement in their overall reflection scores, suggesting that automated feedback improves reflection quality. Furthermore, most of the students reported that reflective writing improved their learning experience, citing benefits such as increased self-awareness, better project and time management, and enhanced technical skills.

Paper Citation

in Harvard Style

Anand B. and Long Q. (2025). iReflect: Enhancing Reflective Learning with LLMs: A Study on Automated Feedback in Project Based Courses. In Proceedings of the 17th International Conference on Computer Supported Education - Volume 2: CSEDU; ISBN 978-989-758-746-7, SciTePress, pages 395-403. DOI: 10.5220/0013435800003932

in Bibtex Style

@conference{csedu25,
author={Bhojan Anand and Quek Long},
title={iReflect: Enhancing Reflective Learning with LLMs: A Study on Automated Feedback in Project Based Courses},
booktitle={Proceedings of the 17th International Conference on Computer Supported Education - Volume 2: CSEDU},
year={2025},
pages={395-403},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013435800003932},
isbn={978-989-758-746-7},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Conference on Computer Supported Education - Volume 2: CSEDU
TI - iReflect: Enhancing Reflective Learning with LLMs: A Study on Automated Feedback in Project Based Courses
SN - 978-989-758-746-7
AU - Anand B.
AU - Long Q.
PY - 2025
SP - 395
EP - 403
DO - 10.5220/0013435800003932
PB - SciTePress