Directive, Metacognitive or a Blend of Both? A Comparison of AI-Generated Feedback Types on Student Engagement, Confidence, and Outcomes
Preprint
Abstract
Feedback is one of the most powerful influences on student learning, with extensive research examining how best to implement it in educational settings. Increasingly, feedback is being generated by artificial intelligence (AI), offering scalable and adaptive responses. Two widely studied approaches are directive feedback, which gives explicit explanations and reduces cognitive load to speed up learning, and metacognitive feedback which prompts learners to reflect, track their progress, and develop self-regulated learning (SRL) skills. While both approaches have clear theoretical advantages, their comparative effects on engagement, confidence, and quality of work remain underexplored. This study presents a semester-long randomised controlled trial with 329 students in an introductory design and programming course using an adaptive educational platform. Participants were assigned to receive directive, metacognitive, or hybrid AI-generated feedback that blended elements of both directive and metacognitive feedback. Results showed that revision behaviour differed across feedback conditions, with Hybrid prompting the most revisions compared to Directive and Metacognitive. Confidence ratings were uniformly high, and resource quality outcomes were comparable across conditions. These findings highlight the promise of AI in delivering feedback that balances clarity with reflection. Hybrid approaches, in particular, show potential to combine actionable guidance for immediate improvement with opportunities for self-reflection and metacognitive growth.Keywords
All Related Versions
This publication has 30 references indexed in Scilit:
- Unraveling the mechanisms and effectiveness of AI-assisted feedback in education: A systematic literature reviewComputers and Education Open, 2025
- Emotionally enriched AI-generated feedback: Supporting student well-being without compromising learningComputers & Education, 2025
- Advancing feedback research in educational psychology: Insights into feedback processes and determinants of effectivenessContemporary Educational Psychology, 2025
- Analytics of Learner-Centered Feedback: A Large-Scale Case Study in Higher EducationComputers & Education, 2025
- Assessing the proficiency of large language models in automatic feedback generation: An evaluation studyComputers and Education: Artificial Intelligence, 2024
- Exploring the effect of directive and reflective feedback on elementary school students’ scientific conceptual understanding, epistemological beliefs, and inquiry performance in online inquiry activitiesResearch in Science Education, 2024
- Impact of AI assistance on student agencyComputers & Education, 2023
- The impact of feedback on metacognition: Enhancing in easy tasks, impeding in difficult onesConsciousness and Cognition, 2023
- Understanding the impact of guiding inquiry: the relationship between directive support, student attributes, and transfer of knowledge, attitudes, and behaviours in inquiry learningInstructional Science, 2017
- Metacognitive theoriesEducational Psychology Review, 1995