AI-assisted peer feedback enhanced lexical diversity only in the first writing task, with the group advantage disappearing by the second task¶
Claim · All claims
Evidence · 1 study · causalr2·q3·i3large
Currency · newest study 2026 · checked against its sources 2026-10-20 (automated, 1 of 1 entry) · not reviewed by a person
Subclaims¶
Reading the evidence codes
q is the design tier, i the impact, n the sample, and the kind with its r
the rigour judged within that kind: what each code means.
This claim: no standardized effect is recorded in observations/ for it yet, so no benchmark reading is possible.
q3 i3 In the first task the AI-assisted peer feedback class significantly outperformed the teacher feedback class on lexical diversity (F(1,59)=12.288, p < .001; group main effect ηp² = .200), but in the second task the group effect was non-significant (F(1,59)=1.084, p = .303). → Tang J 2026
Evidence¶
Tang J 2026¶
Tang J, Li P, Luo R (2026) Teacher feedback VS AI-assisted peer feedback in L2 writing: A quasi-experimental study in a Chinese University. PLoS One 21(6): e0345976. https://doi.org/10.1371/journal.pone.0345976
q3 · i3 · causal · r2
Mixed repeated-measures ANOVA on Coh-Metrix 3.0 lexical diversity indicators (LDTTRc, LDMTLDa, LDVOCDa) across two tasks; first-task group main effect ηp² = .200 (large), second task ηp² = .022. The authors say the advantage was not "internalized into a stable lexical generation strategy".
"the AI-assisted peer feedback class performed significantly better in lexical diversity than the teacher feedback class (F(1,59)=12.288, p < .001). However, this advantage disappeared in the second task, with the main effect of group no longer being significant (F(1,59)=1.084, p = .303)"
Discussion¶
Related Claims¶
- AI-peer integrated feedback yields significant gains on all four writing dimensions, with the group × dimension interaction showing differential improvement favoring task achievement and lexical resource over coherence and cohesion — related
- Neither feedback mode produced differential improvements in syntactic complexity; a general time effect appeared only in the first task — related
- In the first writing task, teacher feedback contained significantly more items than AI-assisted peer feedback, especially on vocabulary errors and technical details — related
- Free ChatGPT use boosts originality on the assisted creative task but the advantage disappears when assistance is removed — related
- Teacher feedback produced larger first-task score gains that dropped 32.8% by the second task, while AI-assisted peer feedback gains remained stable (a learning-curve effect) — related
- Peer assessment of writing yields outcomes at least as good as teacher assessment and sometimes better — related
- AI-assisted journal entries show higher lexical diversity and more emotion-word usage than unassisted entries — related
- Across tasks, teacher feedback shifted from basic error correction toward higher-order dimensions while AI-assisted peer feedback reduced content suggestions and increased technical-detail feedback — related
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
lexical-diversity-advantage-first-task-only |
title |
AI-assisted peer feedback enhanced lexical diversity only in the first writing task, with the group advantage disappearing by the second task |
description |
AI-assisted peer feedback enhanced lexical diversity only in the first writing task, with the group advantage disappearing by the second task |
status |
review |
evidence_strength |
moderate |
newest_evidence |
2026 |
source_checked |
2026-10-20 |
generated |
by process:wiki-ingest on 2026-10-11 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — tang-j-2026 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.