SCRIPT serves as a research platform enabling keystroke-level data collection and controlled comparison of ITS components¶
Claim · All claims
Evidence · 1 study · designr?·q1
Currency · newest study 2025 · 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.
q1 i? The ITS records fine-grained keystroke-level data and supports testing different learner models, outer-loop task selection models, and feedback generation strategies, and has already supported data collection for published learner model and feedback research. → Alina Deriyeva 2025
Evidence¶
Alina Deriyeva 2025¶
Alina Deriyeva, Jesper Dannath, and Benjamin Paaßen. (2025). SCRIPT: Implementing an Intelligent Tutoring System for Programming in a German University Context. Artificial Intelligence in Education (Springer). https://doi.org/10.1007/978-3-031-99261-2_16
q1 · i? · design · r?
Descriptive statement (type d) about the system's research function: it enables investigating which knowledge tracing models best represent user performance, which task/intervention suggestion models support skill acquisition, and what hints to give in which situations. The article notes it has already supported data collection for learner model and feedback research (Dannath et al. 2024, 2025; Deriyeva et al. 2024).
"The ITS also serves as a research platform, in the sense that it allows testing different educationalstrategiesandtools, andallowscollectingdetaileddataaboutlearninginteractions of the users (currently at the key-stroke level)."
Discussion¶
Related Claims¶
- AI tools collected and organized a previously unavailable granularity of data, including individual student exchanges and classroom discussion data, to generate actionable recommendations — related
- A four-state semi-Markov model distinguishing jump editing from local editing fits keystroke-log writing data significantly better than a three-state model — related
- Screen reader choice affects time and effort for accessing math: JAWS users completed a quadratic-equation task faster than NVDA users — related
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
script-research-platform-data-collection |
title |
SCRIPT serves as a research platform enabling keystroke-level data collection and controlled comparison of ITS components |
description |
SCRIPT serves as a research platform enabling keystroke-level data collection and controlled comparison of ITS components |
status |
review |
evidence_strength |
weak |
newest_evidence |
2025 |
generated |
by process:wiki-ingest on 2026-10-11 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — alina-deriyeva-2025 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.