Strategy-based temporal analytics framework for stealth assessment using LSTM evidence models

Research Method · All research methods
Evidence · 4 claims (4 for) · 3 studies (3 design), q2 · 0 of 3 report an effect size · 4 claims rest on one study

Description

A stealth assessment framework that derives temporal evidence from students' dynamic in-game strategy use rather than only from ECD evidence modeling. Student flip sequences are encoded as n-grams, clustered per task with EM clustering to yield strategy labels, and sequences of strategy cluster memberships across consecutive tasks are fed to an LSTM evidence model that predicts post-test performance. The article states the approach "does not require a labor -intensive process of labeling data" because strategies are discovered unsupervised from log data.

Accounts

• Strategy-based temporal analytics framework for stealth assessment using LSTM evidence models: A stealth assessment framework that derives temporal evidence from students' dynamic in-game strategy use rather than only from ECD evidence modeling. Student flip sequences are encoded as n-grams, clustered per task with EM clustering to yield strategy labels, and sequences of strategy cluster memberships across consecutive tasks are fed to an LSTM evidence model that predicts post-test performance. The article states the approach "does not require a labor -intensive process of labeling data" because strategies are discovered unsupervised from log data. (Akram et al. (2017))

Claims

• An LSTM-based strategy temporal analytics framework outperforms random forest, SVM, and majority-class baselines for stealth assessment predictive accuracy [+M]
• Adding in-game strategy features to pre-test features substantially improves LSTM-based stealth assessment accuracy [+M]
• Clustering n-gram flip sequences per task yields three distinct problem-solving strategy groups across the binary challenges [+M]
• GRU is the lowest-performing model across both single-task and multi-task competency modeling, likely due to its two gating units versus LSTMs' three [+W]

Related Research Methods

• Retrospective emulation of evidence-centered design features for learning analytics
• Evidence-Centered Design

Key Sources

• Akram, B., Mott, B., Min, W., Boyer, K. E., Wiebe, E., & Lester, J. (2017). Improving Stealth Assessment in Game-based Learning with LSTM-based Analytics. https://scholar.google.com/scholar?q=Improving+Stealth+Assessment+in+Game-based+Learning+with+LSTM-based+Analytics

Page metadata

Field	Value
type	research-method
id	strategy-based-temporal-analytics-framework-for-stealth-assessment-using-lstm-evidence-mod
title	Strategy-based temporal analytics framework for stealth assessment using LSTM evidence models
description	A stealth assessment framework that derives temporal evidence from students' dynamic in-game strategy use rather than only from ECD evidence modeling.
status	review
generated	by process:settle-candidates on 2026-10-16
trust	unverified — no one has confirmed this page's content

Frontmatter is the page's machine-readable record — see the Schema & Guide.