Personalized ChatGPT-supported feedback in an augmented-reality quantum physics laboratory improved learning outcomes and directed visual attention¶

Claim · All claims
Evidence · 1 study · review r3 · q3 · i2 medium
Currency · newest study 2026 · checked against its sources 2026-10-18 (automated, 1 of 1 entry) · not reviewed by a person

Subclaims¶

q3 i2 In a randomized controlled study by Coban et al. (2025), students receiving personalized ChatGPT-supported feedback showed significantly higher learning outcomes, with reported effect sizes d = 0.495–1.892. → Malikova Z 2026

Evidence¶

Malikova Z 2026¶

Malikova Z, Ualikhanova B, Turmambekov T, Rakhashev B and Berdaliyev D (2026). Artificial intelligence in university physics education: a systematic review of empirical studies. Front. Educ. 11:1964629. https://doi.org/10.3389/feduc.2026.1964629

q3 · i2 · review · r3

The review reports this randomized controlled trial (21 student groups) in Section 3.4; Table 5 lists the reported statistical indicator "d = 0.495–1.892" for learning outcomes and eye-tracking, noting feedback also "directed visual attention."

"Coban et al. (2025) reported significantly higher learning outcomes for students receiving personalized ChatGPT-supported feedback in an augmented-reality quantum physics laboratory."

Discussion¶

Learner Variables¶

• Attention — outcome: instruction changes it
• Visual Processing — outcome: instruction changes it

Related Claims¶

• AI-mediated feedback in hands-on exhibits improves learning and engagement — related
• As cited second-hand in an AI-literacy framework paper: ChatGPT use improved short-term essay scores but triggered metacognitive laziness with no significant knowledge-transfer gains — related
• A tablet-based AR app displaying real-time measurement data above circuit components aided conceptual knowledge acquisition more effectively than traditional physics lab lessons — related
• Students report heightened autonomy in English learning through self-directed regulation, personalized feedback, and active evaluation of ChatGPT suggestions — related
• Optional IBM Quantum hardware execution supplied extra evidence but did not remove substantial AI assistance, as ChatGPT generated the code and could interpret returned noisy data — related
• The review reports AI-driven personalization improves student engagement and learning outcomes, and virtual teaching assistants support diverse learning needs — a broader claim this one bears on
• The authors of three case studies (roughly 28 students) argue that a place-based augmented reality game, Mad City Mystery, holds potential for engaging students in scientific argumentation — related
• Students receiving instructor feedback showed significantly greater improvements in lab assignment scores than students receiving AI-generated feedback, after controlling for initial knowledge — related
• Students perceived online lab exercises as more effective when instructors were present online and used scaffolds and probes directing attention to key procedure aspects — related