Students receiving intelligent ITS feedback spent significantly more time and made significantly more steps on the hypothesis-testing tasks than controls¶
Claim · All claims
Evidence · 1 study (2 entries) · causalr2·q3·i1small
Currency · newest study 2020 · not yet checked against its sources · not reviewed by a person
Design limits · Tacoma 2020: the intervention came bundled with another change (read from the study by two models, 2026-10-28)
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 i1 Experimental-group students worked 41 min (SD=27) versus 32 min (SD=19) in the control group, a significant difference with Cohen's d = 0.38. → Tacoma 2020
q3 i1 Experimental-group students made significantly more steps (M=8.0, SD=5.4) than controls (M=6.7, SD=3.9), with Cohen's d = 0.27. → Tacoma 2020 (2)
Evidence¶
Tacoma 2020¶
Tacoma, S., Heeren, B., Jeuring, J., & Drijvers, P. (2020). Intelligent Feedback on Hypothesis Testing. International Journal of Artificial Intelligence in Education. https://doi.org/10.1007/s40593-020-00218-y
q3 · i1 · causal · r2
Welch two-sample t-test comparing total time on the six hypothesis-testing construction tasks between the randomized groups in the course-embedded experiment. The experimental group worked significantly longer, with "Cohen’s d = 0.38".
"in the experimental group this was 41 min ( SD = 27 min) and in the control group it was 32 min ( SD =1 9 m i n ) , a significant difference (t(291.8) = 3.41, p < .001, Cohen’s d = 0.38)"
Tacoma 2020 (2)¶
Tacoma, S., Heeren, B., Jeuring, J., & Drijvers, P. (2020). Intelligent Feedback on Hypothesis Testing. International Journal of Artificial Intelligence in Education. https://doi.org/10.1007/s40593-020-00218-y
q3 · i1 · causal · r2
Independent-samples t-test on the mean number of steps students selected across the six tasks. The experimental group made significantly more steps, with "Cohen ’s d = 0.27". The article notes students also received feedback regularly, averaging two hint requests per student per task.
"Students in the experimental group made slightly but significantly more steps (M =8 . 0 ,SD = 5.4) than students in the control group ( M= 6.7, SD = 3.9, t(293.7) = 2.41, p = .016, Cohen ’s d = 0.27)"
Discussion¶
Related Claims¶
- Students receiving intelligent ITS feedback made significantly fewer errors in hypothesis-testing logic than students receiving verification feedback only — related
- ITS feedback availability interacted with task number so that experimental-group students increasingly outperformed controls in solving tasks over time — related
- The number of tasks students worked on and attempted step construction for did not differ significantly between feedback conditions — reports the opposite
- Effects of intelligent ITS feedback did not transfer to follow-up hypothesis-testing tasks without intelligent feedback — related
- The experimental group spent significantly more time per problem and completed significantly fewer problems than the control group — related
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
its-feedback-more-time-and-steps |
title |
Students receiving intelligent ITS feedback spent significantly more time and made significantly more steps on the hypothesis-testing tasks than controls |
description |
Students receiving intelligent ITS feedback spent significantly more time and made significantly more steps on the hypothesis-testing tasks than controls |
status |
review |
evidence_strength |
moderate |
newest_evidence |
2020 |
generated |
by process:wiki-ingest on 2026-10-28 |
trust |
unverified — no one has confirmed this page's content |
sources |
2 — tacoma-2020, tacoma-2020-2 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.