Students' argumentative essay quality improves substantially from initial to revised drafts regardless of feedback source¶

Claim · All claims
Evidence · 1 study · causal r2 · q3 · i3 large
Currency · newest study 2026 · checked against its sources 2026-10-16 (automated, 1 of 1 entry) · not reviewed by a person

Subclaims¶

q3 i3 A repeated-measures ANOVA revealed a significant large main effect of time on essay quality across all three feedback conditions. → Farrokhnia 2026

Evidence¶

Farrokhnia 2026¶

Farrokhnia, M., Latifi, S., Papadopoulos, P. M., Hogenkamp, L., Gijlers, H., Khosravi, H., & Noroozi, O. (2026). Generative AI offers more, but students revise less: comparing the effects of teacher and AI feedback on student essay revisions. International Journal of Educational Technology in Higher Education. https://doi.org/10.1186/s41239-026-00579-9

q3 · i3 · causal · r2

Repeated-measures ANOVA across the three conditions (total N = 70) showed a significant main effect of time from initial to revised drafts with partial ηp2 = .79, "indicating a large effect size"; descriptive means rose in every condition.

"This was further supported by a repeated measures ANOVA, which revealed a significant main effect of time, F(1, 67) = 255.82, p < .001, partial ηp2 = .79, indicating a large effect size."

Studies bearing on this claim¶

Does working through cycles of attempt, feedback and revision improve the quality of learners' work? This table gathers the studies behind this claim and the 9 narrower claims that bear on it: 9 distinct studies (3 qualitative, 2 causal, 2 design, 2 associational), q1–q3, 1 of 9 with an effect size coded. One row per study, codes as each entry records them; no effect is averaged and no verdict is drawn. Built by scripts/synthesize_claim.py from eval/synthesis/; a row that looks wrong is fixed on the claim it comes from.

Discussion¶

Learner Variables¶

• Writing Skills — outcome: instruction changes it

Related Claims¶

• Process Writing Improves Writing Quality — the general claim this finding bears on, with the studies behind it
• Chain-of-thought prompting yields higher-quality GenAI feedback on argumentative essays than Zero-shot prompting and teacher feedback — related
• Feedback source does not significantly affect revised essay quality once initial draft quality is controlled — related
• In one study, feedback quality significantly predicts revised essay quality under teacher feedback but not under either GenAI feedback condition, though the conditions are not compared directly — related
• GenAI feedback quality correlates with initial essay quality while teacher feedback quality does not — related
• Students in a scaffolded LLM-collaboration course improved significantly on initial argument quality, prompt engineering, and response to AI feedback from the first to the fifth assignment — related
• Children's plan quality improves substantially after receiving LLM-generated adaptive feedback — related
• Lasting pedagogical change is more likely when teachers try out strategies, receive feedback, and iteratively improve across multiple workshops — related
• Lesson-plan quality grows steadily across three iterative design rounds, but no product reaches the excellent grade — related
• Students became better able to develop arguments even prior to interacting with LLMs, per the authors' interpretation of initial-draft gains — related
• Dwell time on the essay correlates positively with the quality of revised essays as assessed by professors — related