That's Not the Feedback I Need! -- Student Engagement with GenAI Feedback in the Tutor Kai

2025-06-25

AI Summary

This study investigates how computing students interactively leverage generative AI (GenAI) and compiler feedback during Python programming learning, and evaluates their respective support for problem-solving skill development. Method: We designed a custom web platform integrating programming tasks, an embedded code editor, and dual-source feedback (GenAI + compiler), complemented by eye-tracking and semi-structured interviews to achieve unprecedented integration of quantitative gaze metrics with qualitative interpretive analysis. Contribution/Results: Novices spent twice as long fixating on GenAI feedback as experts but frequently overlooked compiler feedback and struggled to interpret GenAI outputs; experts, though issuing fewer queries, demonstrated significantly higher feedback adoption rates and solution-transformation efficiency. The findings reveal experience level as a critical moderator of GenAI feedback efficacy, uncovering underlying cognitive mechanisms in AI-assisted debugging. This work provides empirically grounded design principles and pedagogical guidelines for AI-enhanced programming education.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Humans and AI: User Experience and Usability
• Cognitive Modeling & Cognitive Systems: Computational Creativity

Application Category

• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

The potential of Generative AI (GenAI) for generating feedback in computing education has been the subject of numerous studies. However, there is still limited research on how computing students engage with this feedback and to what extent it supports their problem-solving. For this reason, we built a custom web application providing students with Python programming tasks, a code editor, GenAI feedback, and compiler feedback. Via a think-aloud protocol including eye-tracking and a post-interview with 11 undergraduate students, we investigate (1) how much attention the generated feedback received from learners and (2) to what extent the generated feedback is helpful (or not). In addition, students' attention to GenAI feedback is compared with that towards the compiler feedback. We further investigate differences between students with and without prior programming experience. The findings indicate that GenAI feedback generally receives a lot of visual attention, with inexperienced students spending twice as much fixation time. More experienced students requested GenAI less frequently, and could utilize it better to solve the given problem. It was more challenging for inexperienced students to do so, as they could not always comprehend the GenAI feedback. They often relied solely on the GenAI feedback, while compiler feedback was not read. Understanding students' attention and perception toward GenAI feedback is crucial for developing educational tools that support student learning.

Problem

• How computing students engage with GenAI feedback
• Effectiveness of GenAI feedback in problem-solving
• Differences in engagement between novice and experienced students

Innovation

• Custom web app with GenAI feedback
• Eye-tracking to measure feedback attention
• Compare GenAI and compiler feedback usage