Adding contextualized emotion features to a worksheet-submission baseline model significantly improved prediction of overall game score¶
Claim · All claims
Evidence · 1 study · associationalr2·q3
Currency · newest study 2019 · 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? A nested F-test showed the full model including emotion features significantly improved on the reduced model using only total worksheet submissions (F(6, 53) = 3.54, p < 0.01), with cross-validation R2 improving from 0.191 to 0.285. → Michelle Taub 2019
Evidence¶
Michelle Taub 2019¶
Michelle Taub, Robert Sawyer, James Lester, Roger Azevedo. (2019). The Impact of Contextualized Emotions on Self-Regulated Learning and Scientific Reasoning during Learning with a Game-Based Learning Environment. International Journal of Artificial Intelligence in Education. https://doi.org/10.1007/s40593-019-00191-1
q3 · i? · associational · r2
Model comparison in the CRYSTAL ISLAND regression analysis. The nested F-test, "F(6, 53) = 3.54, p <0 . 0 1", showed the emotion-feature model improved on the baseline; the article reports cross-validation R2 of 0.285 for the full model versus 0.191 for the reduced model, a 9.4% reduction in held-out mean squared error.
"A nested F-test using the full model specified in Table 6 and the reduced model using the strong baseline predictor of total worksheet submits indicates a significant improvement in sum of squared error for the number of parameters introduced F(6, 53) = 3.54, p <0 . 0 1 ."
Discussion¶
Related Claims¶
- Joy during relevant book reading and confusion after positive scans positively predicted overall game score, while total worksheet submissions negatively predicted it — possibly the same claim (merge candidate)
- Dialogue act features raise regression R² but do not significantly improve outcome prediction over a prior-performance baseline — related
- No significant correlations between contextual emotion differences and overall game score after Holm-Bonferroni correction — related
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
emotion-features-improve-over-baseline-model |
title |
Adding contextualized emotion features to a worksheet-submission baseline model significantly improved prediction of overall game score |
description |
Adding contextualized emotion features to a worksheet-submission baseline model significantly improved prediction of overall game score |
status |
review |
evidence_strength |
moderate |
newest_evidence |
2019 |
generated |
by process:wiki-ingest on 2026-10-28 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — michelle-taub-2019 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.