An LSTM-based strategy temporal analytics framework outperforms random forest, SVM, and majority-class baselines for stealth assessment predictive accuracy¶
Claim · All claims
Evidence · 1 study · designr2·q2
Currency · newest study 2018 · checked against its sources 2026-10-20 (automated, 1 of 1 entry) · not reviewed by a person · overdue for a recheck since 2021: 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? The LSTM-based evidence model achieved higher predictive accuracy (64.82%) than random forest (50.43%), SVM (41.17%), and the majority-class baseline (35.71%) on held-out test data. → Akram 2018
Evidence¶
Akram 2018¶
Akram, B., Mott, B., Min, W., Boyer, K. E., Wiebe, E., & Lester, J. (2018). Improving Stealth Assessment in Game-based Learning with LSTM-based Analytics. In Proceedings of the 11th International Conference on Educational Data Mining (EDM 2018). https://scholar.google.com/scholar?q=Improving+Stealth+Assessment+in+Game-based+Learning+with+LSTM-based+Analytics
q2 · i? · design · r2
Computational evaluation on behavior trace data from 168 middle school students who completed both tests and all 11 binary tasks, with training/test split and 100 training runs averaged. The LSTM achieved "an average accuracy of 64.82%" versus RF 50.43%, SVM 41.17%, and baseline 35.71% (Table 2).
"The results of applying this LSTM on the held -out test set achieve an average accuracy of 64.82%, an average precision of 63.88%, an average recall of 65.14%, and an F1-score of 63.68%."
Discussion¶
Related Claims¶
- Adding in-game strategy features to pre-test features substantially improves LSTM-based stealth assessment accuracy
- Random forest algorithms yielded the best classification performance in K–8 MMLA studies comparing multiple machine learning models — reports the opposite
- A random forest classified flagged versus non-flagged word problems with the best accuracy of five tested models (AUC = 0.75) — reports the opposite
- A support vector machine classifier outperformed decision tree and random forest models in predicting cognitive engagement levels of online discussion posts — reports the opposite
- All three trained classifiers outperformed the zero-rule baseline (28.4% accuracy) for classifying cognitive engagement in discussion posts — related
- Random forest achieves the highest mean test accuracy (0.9590) of all models compared for predicting exam grade categories from physiological signals — reports the opposite
- Decision trees achieve competitive accuracy with black-box models (LR, RF, SVM), which performed slightly better but lack interpretability — reports the opposite
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
lstm-strategy-temporal-analytics-outperforms-baselines |
title |
An LSTM-based strategy temporal analytics framework outperforms random forest, SVM, and majority-class baselines for stealth assessment predictive accuracy |
description |
An LSTM-based strategy temporal analytics framework outperforms random forest, SVM, and majority-class baselines for stealth assessment predictive accuracy |
status |
review |
evidence_strength |
moderate |
newest_evidence |
2018 |
source_checked |
2026-10-20 |
recheck_by |
2021 |
generated |
by process:wiki-ingest on 2026-10-16 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — akram-2018 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.