Data augmentation was critical for ordinal discriminability, with QWK dropping to near-zero without it in the Focus dimension and gains up to +0.346 in severely imbalanced dimensions¶
Claim · All claims
Evidence · 1 study · designr2·q2
Currency · newest study 2026 · not yet checked against its sources · 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? In the ablation study, augmentation improved ordinal agreement in five of six dimensions; without augmentation, Focus QWK dropped to 0.028 and Inference QWK was negative (−0.115). → Firdausi 2026
Evidence¶
Firdausi 2026¶
Firdausi, H.; Wasis; Sholikah, R. W.; Lemantara, J.; Rosyadi, F. D.; Ginardi, R. V. H.; Pradityo, M. H. A.; Hakim, A. R. (2026). Educational Innovation through Automated Essay Scoring: A Multidimensional Framework for Evaluating Critical Thinking in High School Physics Essays. International Journal of Intelligent Engineering and Systems, Vol.19, No.8. https://doi.org/10.22266/ijies2026.0831.09
q2 · i? · design · r2
Ablation study (Results §4.3.1 and Table 12) comparing the best model per dimension with and without augmentation on the held-out test set. The Focus dimension's QWK fell to "near-zero (0.028)" without augmentation; the article attributes this to severe class imbalance.
"The ablation study further highlights the critical role of data augmentation: without it, QWK dropped to near-zero (0.028), confirming that class imbalance severely undermines ordinal discrimination"
Discussion¶
Related Claims¶
- The best AES models per FRISCO dimension reached strong agreement for Situation (QWK 0.728) and Clarity (QWK 0.763) but only fair agreement for Focus, Reason, and Inference in Indonesian physics essays — related
- In the Overview dimension, augmentation produced a marginal QWK decrease (ΔQWK = −0.006) despite improving macro-F1, the only dimension with this trade-off — related
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
augmentation-critical-ordinal-qwk-gains |
title |
Data augmentation was critical for ordinal discriminability, with QWK dropping to near-zero without it in the Focus dimension and gains up to +0.346 in severely imbalanced dimensions |
description |
Data augmentation was critical for ordinal discriminability, with QWK dropping to near-zero without it in the Focus dimension and gains up to +0.346 in severely imbalanced dimensions |
status |
review |
evidence_strength |
moderate |
newest_evidence |
2026 |
recheck_by |
2029 |
generated |
by process:wiki-ingest on 2026-10-10 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — firdausi-2026 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.