The stopping algorithm reduces average assessment duration by about 23.5 minutes¶
Claim · All claims
Evidence · 1 study (2 entries) · designr2·q2
Currency · newest study 2021 · 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.
q2 i? After applying the stopping algorithm, mean duration drops from 93.6 to 70.1 minutes and median from 82.5 to 59.7 minutes. → Matayoshi 2021
q2 i? Students taking longer than three hours show an even more pronounced reduction, with mean duration dropping by over 71 minutes. → Matayoshi 2021 (2)
Evidence¶
Matayoshi 2021¶
Matayoshi, J., Cosyn, E., & Uzun, H. (2021). Are We There Yet? Evaluating the Effectiveness of a Recurrent Neural Network-Based Stopping Algorithm for an Adaptive Assessment. International Journal of Artificial Intelligence in Education. https://doi.org/10.1007/s40593-021-00240-8
q2 · i? · design · r2
Analysis of 45,470 assessments with timing data from the held-out test set. Full-length assessments had mean 93.6 minutes and median 82.5 minutes; after the stopping algorithm (GRU, α = 0.99), the distribution shifts left with mean 70.1 and median 59.7 minutes.
"the mean and median durations now being 70.1 minutes and 59.7 minutes, respectively. Thus, after applying the stopping algorithm, over half of the students are able to finish the assessment in less than an hour, with the average assessment duration being reduced by about 23.5 minutes."
Matayoshi 2021 (2)¶
Matayoshi, J., Cosyn, E., & Uzun, H. (2021). Are We There Yet? Evaluating the Effectiveness of a Recurrent Neural Network-Based Stopping Algorithm for an Adaptive Assessment. International Journal of Artificial Intelligence in Education. https://doi.org/10.1007/s40593-021-00240-8
q2 · i? · design · r2
Analysis of the right tail of the duration distribution. The number of assessments longer than three hours drops from 3483 to 1299, a reduction by a factor of approximately 2.7, with mean questions dropping to 19.4.
"There are 3483 students who took longer than three hours to complete the assessment; these students have a mean duration of approximately 221.1 minutes. After applying the stopping algorithm, the mean duration for these students drops to 149.8 minutes"
Discussion¶
Related Claims¶
- An RNN-based stopping algorithm reduces ALEKS PPL assessment length by over 26% while maintaining high accuracy — possibly the same claim (merge candidate)
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
stopping-algorithm-reduces-assessment-duration |
title |
The stopping algorithm reduces average assessment duration by about 23.5 minutes |
description |
The stopping algorithm reduces average assessment duration by about 23.5 minutes |
status |
review |
evidence_strength |
moderate |
newest_evidence |
2021 |
generated |
by process:wiki-ingest on 2026-10-28 |
trust |
unverified — no one has confirmed this page's content |
sources |
2 — matayoshi-2021, matayoshi-2021-2 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.