ORIGINAL RESEARCH article
Front. Psychol.
Sec. Educational Psychology
Psychological Engagement with Automated Design Improvement Feedback: A Multiple Case Study of ChatGPT in Design Education
Provisionally accepted
- 1Raffles College of Higher Education, Singapore, Singapore
- 2Central South University, Changsha, China
- 3Jiangsu University of Technology, Changzhou, China
- 4Zhejiang University, Hangzhou, China
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Understanding the psychological mechanisms underlying student engagement with AI-driven feedback represents a critical priority in educational psychology. With the emergence of ChatGPT as a generative artificial intelligence (GAI) tool, the application methods and potential of automated design improvement feedback (ADIF) have been expanded. However, understanding how students behaviorally, cognitively, and emotionally engage with AI-driven feedback in design education remains an understudied area in educational psychology. Grounded in self-regulated learning theory and educational psychology frameworks, a mixed-method multiple case study investigated 50 design major students during a single product design session, examining their behavioral, cognitive, and emotional engagement when using ChatGPT for ADIF. The findings reveal distinct engagement patterns across performance levels. High performers employed diverse prompt construction strategies and iterative query refinement behaviors. Low performers predominantly utilized basic prompts with limited iterations. Sequential analysis revealed that high performers exhibited significant cyclical transitions between metacognitive states. Low performers demonstrated linear progressions from query to implementation. High performers characterized their AI interactions as exploratory and collaborative. Low performers described structured guidance-seeking interactions. This study contributes to educational psychology by elucidating the psychological mechanisms underlying differential engagement with AI-driven feedback. The findings extend self-regulated learning theory to human-AI interaction contexts, revealing how individual differences in metacognitive capabilities systematically shape behavioral strategies, cognitive processing patterns, and emotional responses. For practical implementation, the study demonstrates the need for psychologically-informed scaffolding strategies when deploying AI-assisted feedback systems, particularly interventions that support lower-performing students in developing metacognitive and strategic capabilities for effective AI interaction. The exploratory study offers initial insights for researchers interested in understanding differential student engagement with GAI-based systems and contributes to ongoing discussions about performance-based variations in human-AI collaboration within educational contexts.
Keywords: AI-assisted feedback systems1, ChatGPT3, Design5, Education2, psychological engagement4
Received: 19 Jan 2026; Accepted: 26 Jan 2026.
Copyright: © 2026 Wu, Zeng, Li, Li, Chen, Sun, Zhu and Xie. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence:
Xinyu Li
Liangliang Zhu
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.