Related Experiment Videos
AI Versus Human Feedback in Gamified Color Education: A Four-Arm Cluster Randomized Controlled Trial
Xiheng Shao1, Fulong Liu2, Jiao Wu1
1Centre for Instructional Technology and Multimedia, Universiti Sains Malaysia, Jalan Universiti, Gelugor 11700, Pulau Pinang, Malaysia.
Behavioral Sciences (Basel, Switzerland)
|July 28, 2026
Summary
Gamification with AI feedback improved metacognitive regulation in undergraduate color education. Prior AI credibility belief tentatively suggested benefits for learners with higher trust in AI systems.
Area of Science:
- Educational Technology
- Artificial Intelligence in Education
- Cognitive Psychology
Background:
- Empirical evidence on AI formative assessment combined with gamification is limited in aesthetic disciplines.
- Metacognitive regulation is crucial for learning, especially in subjective fields like color education.
- Learner beliefs about Artificial Intelligence (AI) credibility may influence the effectiveness of AI-driven educational interventions.
Purpose of the Study:
- To investigate if integrating AI formative assessment with gamification enhances metacognitive regulation in undergraduate color education.
- To determine if the effects of AI-gamification are conditional on learners' prior beliefs about AI credibility.
- To explore the longitudinal impact of this integration on motivation and achievement.
Main Methods:
- A four-arm, cluster-randomized controlled trial with 540 undergraduates across 24 classes.
- Comparison of four conditions: gamification with AI feedback, gamification with human feedback, gamification only, and traditional instruction.
- Measurement of metacognitive regulation, motivation, and achievement over four waves, with a primary outcome assessed 4 weeks post-intervention.
Main Results:
- Gamification significantly improved metacognitive regulation compared to traditional instruction (d = 0.34, p < 0.05).
- No significant average difference was found between AI feedback and human feedback (d = 0.07), though this comparison was underpowered.
- Metacognitive regulation longitudinally mediated the intervention's effects on motivation and achievement.
- Prior AI credibility belief tentatively moderated the indirect effect on motivation, with higher-belief learners showing greater benefit.
Conclusions:
- Gamification shows promise for enhancing metacognitive regulation in aesthetic education.
- AI formative assessment integrated with gamification may be beneficial, particularly for learners with higher prior trust in AI.
- Findings extend self-determination theory and self-regulated learning frameworks to aesthetic education, suggesting a need for trust-aware AI feedback deployment.