Decision tree classifiers trained on slide interaction features predict end-of-module outcomes with high accuracy across four K-12 programming courses¶
Claim · All claims
Evidence · 1 study · associationalr2·q2
Currency · newest study 2025 · not yet checked against its sources · not reviewed by a person · recheck by 2028: 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? DTs with and without feature selection achieved 85.2-90.7% accuracy, 0.88-0.92 precision, 0.78-0.98 recall and 0.83-0.92 F1 across all four courses, considerably surpassing the majority-class baseline. → Vincent Zhang 2025
Evidence¶
Vincent Zhang 2025¶
Vincent Zhang, Bryn Jeffries, Irena Koprinska. (2025). A Machine Learning Approach for Predicting Student Progress in Online Programming Education. Int J Artif Intell Educ. https://doi.org/10.1007/s40593-025-00510-9
q2 · i? · associational · r2
Evaluation on log data from four large-scale online programming courses (approximately 35,000 enrolled students), with a separate DT model per module and 10-fold stratified cross-validation. The article reports "85.2-90.7% accuracy" for DTs with and without feature selection, all surpassing the majority-class baseline.
"The DTs with and without feature selection show consistently high predictive performance on all courses - 85.2-90.7% accuracy, precision of 0.88-0.92 precision, 0.78-0.98 recall and 0.83-0.92 F1 score. All DTs considerably surpass the majority class baseline."
Discussion¶
Related Claims¶
- Decision trees achieve competitive accuracy with black-box models (LR, RF, SVM), which performed slightly better but lack interpretability — related
- Random forest algorithms yielded the best classification performance in K–8 MMLA studies comparing multiple machine learning models — related
- CFS and GR feature selection shrink decision trees to 3.2-4.7 leaf nodes without degrading predictive performance — related
- Completion of prior problem slides is the most critical predictor of completing a module's final exercise, consistent with the doer effect — a narrower finding that bears on this claim
- A support vector machine classifier outperformed decision tree and random forest models in predicting cognitive engagement levels of online discussion posts — related
- All three trained classifiers outperformed the zero-rule baseline (28.4% accuracy) for classifying cognitive engagement in discussion posts — related
- A random forest classified flagged versus non-flagged word problems with the best accuracy of five tested models (AUC = 0.75) — related
- Academic word list count, word count, and Flesch-Kincaid grade level are the most important features for predicting cognitive engagement in discussion posts — related
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
dt-slide-interaction-features-predict-module-outcomes |
title |
Decision tree classifiers trained on slide interaction features predict end-of-module outcomes with high accuracy across four K-12 programming courses |
description |
Decision tree classifiers trained on slide interaction features predict end-of-module outcomes with high accuracy across four K-12 programming courses |
status |
review |
evidence_strength |
moderate |
newest_evidence |
2025 |
recheck_by |
2028 |
generated |
by process:wiki-ingest on 2026-10-12 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — vincent-zhang-2025 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.