AEEGS scores show high absolute agreement with 12 human expert raters' scores on mathematical Economics essay items (average-measures ICC = 0.863)¶
Claim · All claims
Evidence · 1 study · associationalr2·q2
Currency · newest study 2026 · checked against its sources 2026-10-19 (automated, 1 of 1 entry) · not reviewed by a person · recheck by 2029: tool and model accuracy changes quickly
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.
q2 i? The intra-class correlation coefficient of absolute agreement between AEEGS and 12 human raters was 0.863 at average measures (0.758 single measures), statistically significant at p < .001. → Olaoye DD 2026
Evidence¶
Olaoye DD 2026¶
Olaoye DD, Owolabi HO and Olaoye OT (2026). Automated software scoring of senior school certificate examination mathematical items in economics using a contextual similarity model. Front. Educ. 11:1669504. https://doi.org/10.3389/feduc.2026.1669504
q2 · i? · associational · r2
Correlational study comparing AEEGS scores with those of 12 human raters, each marking 84 of 1,008 scripts, using ICC based on a two-way mixed effect model with absolute agreement. The article reports "good reliability at single measures with 0.758" and 0.863 at average measures, F(1,007, 1,007) = 7.27, p < .001.
"The results displayed in Table 6 revealed good reliability at single measures with 0.758 and higher reliability at average measures with 0.863 while the F(1,007, 1,007) = 7.27, p < .001"
Discussion¶
Related Claims¶
- Each of the 12 human raters' scores correlates significantly with AEEGS scores, with coefficients ranging from 0.604 to 0.864 — a narrower finding that bears on this claim
- AEEGS and human raters produced nearly equivalent, low mean scores (5.94 vs 5.97 of 20), with AEEGS slightly higher — related
- AEEGS and human raters produced similarly shaped score distributions, with most students' scores clustered around the mean in the 'good' band — related
- The AEEGS software demonstrated internal consistency of Cronbach alpha 0.86 in trial testing and was validated for face and content validity by three software experts — related
- The automated scoring system's agreement with human raters varied widely by dimension, with information fidelity showing a weak, non-significant correlation — related
- Automated essay scoring can achieve high agreement with human raters but faces calibration constraints — related
- Out-of-the-box LLMs agree with human essay grades far less than human raters agree with each other — related
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
aeegs-high-agreement-human-raters-icc-0863 |
title |
AEEGS scores show high absolute agreement with 12 human expert raters' scores on mathematical Economics essay items (average-measures ICC = 0.863) |
description |
AEEGS scores show high absolute agreement with 12 human expert raters' scores on mathematical Economics essay items (average-measures ICC = 0.863) |
status |
review |
evidence_strength |
moderate |
newest_evidence |
2026 |
source_checked |
2026-10-19 |
recheck_by |
2029 |
generated |
by process:wiki-ingest on 2026-10-10 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — olaoye-dd-2026 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.