Research map / Large language models / AI and society
A Study of Educational Data Mining: Evidence from a Thai University
Ruangsak Trakunphutthirak, Yen Cheung, Vincent C. S. Lee
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use Random Forest instead of Naive Bayes | at-risk student classifier · Average of 4 log datasets | average accuracy: 0.522 -> 0.778 | Improved |
| use Random Forest instead of Decision tree | at-risk student classifier · Average of 4 log datasets | average accuracy: 0.746 -> 0.778 | Improved |
| use application-type attributes (APP) instead of browsing categories (CAT), duration (ablation) | Random Forest · Duration analysis | ROC area: 0.486 -> 0.497 | Mixed |
| use access duration instead of access frequency (ablation) | Random Forest on APP+CAT · Tables 5 and 6 | accuracy: 0.786 -> 0.772 (best 90/10 combos) | Improved |
| combine APP (90%) and CAT (10%) top-correlated attributes instead of APP only (ablation) | Random Forest, duration · Duration analysis | ROC area: 0.497 -> 0.632 | Improved |
| combine APP (90%) and CAT (10%) instead of APP only (ablation) | Random Forest, duration · Duration analysis | accuracy: 0.779 -> 0.786 | Improved |
| combine APP (90%) and CAT (10%) instead of APP only (ablation) | Random Forest, frequency · Frequency analysis | ROC area: 0.450 -> 0.514 | Improved |
| combine APP (90%) and CAT (10%) instead of APP only (ablation) | Random Forest, frequency · Frequency analysis | accuracy: 0.779 -> 0.772 | Hurt |
| use 50%-50% or 40%-60% weighting rather than 90%-10% (ablation) | Random Forest, duration · Duration analysis | accuracy: 0.786 -> 0.765 (40%-60%) | Hurt |
Closest papers by meaning
- The State of Data Curation at NeurIPS: An Assessment of Dataset Development Practices in the Datasets and Benchmarks Track (NeurIPS 2024 · similarity 0.81)
- Scalable Early Childhood Reading Performance Prediction (NeurIPS 2024 · similarity 0.80)
- Cognitive Bias and Reassignment: Who Can Contribute High Quality LLM Data (AAAI 2025 · similarity 0.80)
- Practical Sentiment Analysis for Education: The Power of Student Crowdsourcing (AAAI 2024 · similarity 0.80)
- AD4CD: Causal-Guided Anomaly Detection for Enhancing Cognitive Diagnosis (AAAI 2025 · similarity 0.80)
- An Autoencoder-Like Nonnegative Matrix Co-Factorization for Improved Student Cognitive Modeling (NeurIPS 2024 · similarity 0.79)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
