Most individual argument structure and quality dimensions showed no significant differences across the three peer feedback conditions¶

Claim · All claims
Evidence · 1 study (2 entries) · causal r1–r2 · q2
Currency · newest study 2026 · checked against its sources 2026-10-20 (automated, 2 of 2 entries) · not reviewed by a person

Subclaims¶

q2 i? Claim, data and warrant, and rebuttal claim showed no significant differences across conditions. → Chang 2026 q2 i? Organisation, clarity, relevance, and persuasiveness showed no significant differences across conditions. → Chang 2026 (2)

Evidence¶

Chang 2026¶

Chang, Y., Liu, Q., Lu, Y. & Miao, E. (2026). Leveraging generative AI to facilitate peer feedback in collaborative argumentation learning. International Journal of Educational Technology in Higher Education. https://doi.org/10.1186/s41239-026-00586-w

q2 · i? · causal · r2

Kruskal-Wallis H tests of structural-complexity element gains across the three conditions. Claim, data and warrant, and rebuttal claim were non-significant; data and warrant was marginal (p = 0.057). Equivalence was not tested.

"the three groups did not differ significantly in the other three elements of structural complexity: claim (H = 1.04, p = 0.596, ε2 =-0.02), data and warrant (H = 5.74, p = 0.057, ε2 = 0.08), and rebuttal claim (H = 4.20, p = 0.123, ε2 = 0.05)."

Chang 2026 (2)¶

Chang, Y., Liu, Q., Lu, Y. & Miao, E. (2026). Leveraging generative AI to facilitate peer feedback in collaborative argumentation learning. International Journal of Educational Technology in Higher Education. https://doi.org/10.1186/s41239-026-00586-w

q2 · i? · causal · r1

Kruskal-Wallis H tests of argument-quality dimension gains across the three conditions. Organisation, clarity, relevance, and persuasiveness were non-significant; clarity was marginal (p = 0.056).

"the three groups did not differ significantly in the other four elements of argument quality: organization (H = 3.02, p = 0.221, ε2 = 0.02), clarity (X2 = 5. 77, p = 0.056, ε2 = 0.08), relevance (X2 = 1.96, p = 0.376, ε2 = 0.00), and persuasiveness (X2 = 0.51, p = 0.775, ε2 = 0.00)."

Discussion¶

Related Claims¶

• Argument quality gains favored the PS-GenAI-PF group over the PF group, while elaboration gains favored the GenAI-PF group — related
• GenAI-supported peer feedback groups achieved higher structural complexity of argumentation artifacts than peer-feedback-only groups — related
• GenAI-supported peer feedback groups produced more suggestions and explanations and less positive affective feedback than the PF group — related
• The PS-GenAI-PF group outperformed the PF group on rebuttal data and warrant and on addressing the opposing view — reports the opposite
• Direct GenAI-supported feedback improves immediate argument-quality gain over peer feedback, while reflective and hybrid designs outperform direct GenAI feedback — related