AI-GFCA students report better peer interaction, collaboration, form of interaction and provision of peer feedback, but reception of peer feedback does not differ¶

Claim · All claims
Evidence · 1 study (2 entries) · causal r1 · q2 · i2 medium
Currency · newest study 2025 · checked against its sources 2026-10-29 (automated, 2 of 2 entries) · not reviewed by a person
Design limits · Darmawansah 2025: groups were assigned but students were analysed as independent (read from the study by two models, 2026-10-29)

Subclaims¶

q2 i2 The AI-GFCA group scored higher than the AI-C group on the peer-interaction subscale of the interaction-mindset survey. → Darmawansah 2025 q2 i? Reception of peer feedback did not differ significantly between groups. → Darmawansah 2025 (2)

Evidence¶

Darmawansah 2025¶

Darmawansah, D., Hwang, G.-J., Lin, C.-J., & Febiyani, F. (2025). An artificial intelligence-supported GFCA learning model to enhance L2 students' role-play performance, English speaking and interaction mindset. Education Tech Research Dev (2025) 73:1451–1479. https://doi.org/10.1007/s11423-025-10453-6

q2 · i2 · causal · r1

Mann–Whitney test on the peer-interaction subscale of the 15-item interaction-mindset post-survey (α = 0.69) in the quasi-experiment; peer interaction favored AI-GFCA with "r = 0.32".

"In terms of peer interaction, students in the AI-GFCA group (Mdn = 5) had better peer interaction than students in the AI-C group (Mdn = 4.5) with U = 158.00, z = − 2.176, p = 0.030, and r = 0.32."

Darmawansah 2025 (2)¶

Darmawansah, D., Hwang, G.-J., Lin, C.-J., & Febiyani, F. (2025). An artificial intelligence-supported GFCA learning model to enhance L2 students' role-play performance, English speaking and interaction mindset. Education Tech Research Dev (2025) 73:1451–1479. https://doi.org/10.1007/s11423-025-10453-6

q2 · i? · causal · r1

Null Mann–Whitney result for the reception-of-peer-feedback subscale; no statistically significant group difference was detected and equivalence was not tested.

"in terms of reception of peer feedback, students in the AI-GFCA group (Mdn = 4.33) had a relatively equal level of receiving peer feedback with students in the AI-C group (Mdn = 4.33), with U = 135.50, z = − 1.596."

The article's prose gives U = 135.50 for this subscale, but its Table 7 reports U = 185.00; both give a non-significant difference, which is not evidence that the groups are equal.

Discussion¶

Learner Variables¶

• Collaboration — outcome: instruction changes it
• Social Supports — outcome: instruction changes it

Related Claims¶

• Students in both groups valued the AI speaking app for autonomous practice, and AI-GFCA students reported reduced anxiety and more peer interaction — related
• A feedback provision scaffold of prompts plus a sample solution significantly improves the quality of feedback messages pre-service teachers provide on peers' case analyses — related
• Instructional support improves quality of feedback provision (g = 0.64) and quality of feedback reception (g = 0.49) but not subject-matter-related knowledge — related
• Feedback provision support has a positive medium-sized effect (g = 0.51) whereas feedback reception support shows no significant effect — related