Human evaluators' prioritization of essential features was significantly better for low-quality essays than for average- and high-scoring essays¶
Claim · All claims
Evidence · 1 study · causalr2·q3
Currency · newest study 2023 · not yet checked against its sources · 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 i? Human raters showed a statistically significant difference in prioritization of essential features across essay quality levels (p = .002), with ratings of 4.44 for low-quality essays versus 3.79 and 3.84 for average- and high-scoring essays; other components did not vary. → Steiss 2023
Evidence¶
Steiss 2023¶
Steiss, Jacob; Tate, Tamara; Graham, Steve; Cruz, Jazmin; Hebert, Michael; Wang, Jiali; Moon, Youngsun; Tseng, Waverly; Warschauer, Mark. (2023). Comparing the Quality of Human and ChatGPT Feedback on Students' Writing. https://eric.ed.gov/?q=Comparing+the+Quality+of+Human+and+ChatGPT+Feedback+on+Students+Writing
q3 · i? · causal · r2
ANOVA across essay-quality groups for human feedback found only prioritization varied significantly (p = .002); "Human feedback did not otherwise vary by scoring level of the underlying essays."
"Human raters showed a statistically significant difference in ratings with respect to prioritization of essential features (p = .002), with ratings of 4.44 for low-quality essays but less effective feedback for average- (3.79) and high-scoring (3.84) essays."
Discussion¶
Related Claims¶
- ChatGPT feedback quality varied by essay quality: accuracy declined as essay quality rose, prioritization was best for average essays, and supportive tone was lowest for low-quality essays — related
- Trained human evaluators provided higher-quality formative feedback than ChatGPT on four of five components, while ChatGPT outperformed humans on criteria-based feedback — a broader claim this one bears on
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
human-prioritization-varies-by-essay-quality |
title |
Human evaluators' prioritization of essential features was significantly better for low-quality essays than for average- and high-scoring essays |
description |
Human evaluators' prioritization of essential features was significantly better for low-quality essays than for average- and high-scoring essays |
status |
review |
evidence_strength |
moderate |
newest_evidence |
2023 |
generated |
by process:wiki-ingest on 2026-10-15 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — steiss-2023 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.