More accurate assessment of self-explanation significantly improves the model's assessment of student learning through exploration¶
Claim · All claims
Evidence · 1 study · designr2·q2
Currency · newest study 2005 · not yet checked against its sources · not reviewed by a person · overdue for a recheck since 2008: 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? Each successive model version (no self-explanation, time-only, time plus gaze shifts) increased accuracy of exploration-node assessment, with both ROC-area increases statistically significant at the z > 1.96 level. → Christina Merten and Cristina Conati 2005
Evidence¶
Christina Merten and Cristina Conati 2005¶
Christina Merten and Cristina Conati. (2005). Eye-Tracking to Model and Adapt to User Meta-cognition in Intelligent Learning Environments. https://www.cs.ubc.ca
q2 · i? · design · r2
Exploration-node accuracy was evaluated by comparing final exploration-of-categories probabilities against post-test scores on the corresponding concepts. Table 4 shows combined accuracy rising from 59.0% (model 1) to 71.0% (model 2) to 75.1% (model 3).
"the area under the curve increased with the inclusion of self-explanation to the student model. The addition of gaze shift data also caused an increase. Both of these increases were found to be statistically significant at the z > 1.96 level"
Discussion¶
Related Claims¶
- In an initial eye-tracking study, time on action predicted self-explanation (16-second threshold) and gaze shifts were most reliable at detecting its absence
- Time and gaze-shift evidence are complementary predictors of self-explanation: time alone yields higher sensitivity, gaze shifts alone higher specificity, and the combination the best accuracy
- Adding eye-tracking evidence to ACE's student model significantly improves assessment of implicit self-explanation over a time-only model — a narrower finding that bears on this claim
- Customizing knowledge-node priors from pretest scores improves model accuracy, but tailoring SE-tendency priors yields no significant improvement — related
- Leave-one-out cross-validation over 36 students confirms significant accuracy and stability gains from eye-tracking in both self-explanation and exploration assessment — related
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
se-assessment-improves-exploration-assessment |
title |
More accurate assessment of self-explanation significantly improves the model's assessment of student learning through exploration |
description |
More accurate assessment of self-explanation significantly improves the model's assessment of student learning through exploration |
status |
review |
evidence_strength |
moderate |
newest_evidence |
2005 |
recheck_by |
2008 |
generated |
by process:wiki-ingest on 2026-10-16 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — christina-merten-and-cristina-conati-2005 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.