Use AI-based analysis of student log files to scaffold inquiry competencies and guide teachers in real time¶
Strategy · All strategies
Evidence · 6 claims (4 for, 2 mixed) · 1 study (1 review),q3· 1 of 1 report an effect size · 6 claims rest on one study
Description¶
The article recommends building on log-file analytics to design guidance for inquiry learning: AI algorithms can assess a wide range of inquiry competencies and support students' learning in real time via a digital agent, and AI-driven dashboards can give teachers detailed information to guide inquiry instruction. Specific activities needing guidance include applying the Control of Variables Strategy in multivariable situations, coordinating theory and evidence, and constructing scientific explanations.
Design Implications¶
Context¶
Requirements¶
- Students definitely need guidance for specific inquiry activities such as applying the CVS and coordinating theory and evidence.
Constraints¶
Target Learners¶
- Secondary science students
- Science teachers
Target Learning Goals¶
- Scientific inquiry competencies such as control of variables strategy and scientific explanation construction
Claims¶
- Meta-analysis of 164 studies found assisted inquiry more effective than explicit instruction [+W]
- Well-controlled comparison studies show clear advantages of inquiry-based instruction over direct instruction for science conceptual learning [+W]
- Generative instructional conditions (inquiry and explanation) outperformed receptive conditions on far transfer, with inquiry best on far transfer problems [+W]
- Guided play outperformed direct instruction for executive functioning and numeracy in early childhood, but not for literacy or socioemotional outcomes [~W]
- Large randomized evaluations of project-based learning programs show advantages over traditional science teaching of about 0.2 standard deviations [+W]
- Successful low-prior-knowledge inquiry learners managed cognitive load by exploring simple circuits first and pausing during learning [~W]
Related Strategies¶
Examples¶
-
Key Sources¶
- Ton de Jong, Ard W. Lazonder, Clark A. Chinn, Frank Fischer, Janice Gobert, Cindy E. Hmelo-Silver, Ken R. Koedinger, Joseph S. Krajcik, Eleni A. Kyza, Marcia C. Linn, Margus Pedaste, Katharina Scheiter, Zacharias C. Zacharia. (2024). Beyond inquiry or direct instruction: Pressing issues for designing impactful science learning opportunities. Educational Research Review, 44. https://doi.org/10.1016/j.edurev.2024.100623
Page metadata
| Field | Value |
|---|---|
type |
strategy |
id |
ai-log-file-scaffolding-and-teacher-dashboards-for-inquiry |
title |
Use AI-based analysis of student log files to scaffold inquiry competencies and guide teachers in real time |
description |
The article recommends building on log-file analytics to design guidance for inquiry learning: AI algorithms can assess a wide range of inquiry competencies and support students' learning in real time via a digital ag... |
status |
review |
generated |
by process:wiki-ingest on 2026-10-21 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — ton-de-jong-2024 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.