Use strategy-based evidence models to trigger adaptive scaffolding toward more productive problem-solving strategies¶

Strategy · All strategies
Evidence · 1 claim (1 for) · 1 study (1 design), q2 · 0 of 1 report an effect size · 1 claim rests on one study

Description¶

The article recommends that intelligent game-based learning environments use induced evidence models to infer students' problem-solving strategies from trace data and intervene when a strategy associated with poor outcomes is detected. When the environment detects a poor-outcome strategy, "it can intervene to guide students towards more productive strategies," and evidence models can work with knowledge modeling to support knowledge scaffolding, such as timely explanations of binary digit weights.

Design Implications¶

Context¶

Requirements¶

• Evidence models induced from student behavior trace data, integrated into the game-based learning environment so strategy signals can trigger interventions

Constraints¶

• The scaffolding use is proposed by the authors as future application; the study evaluated predictive accuracy, not scaffolding effectiveness

Target Learners¶

• middle school students solving in-game computational thinking challenges

Target Learning Goals¶

• adopting productive problem-solving strategies and building conceptual knowledge such as binary digit weights

Affordances¶

• Strategy Based Temporal Analytics Stealth Assessment

Claims¶

• An LSTM-based strategy temporal analytics framework outperforms random forest, SVM, and majority-class baselines for stealth assessment predictive accuracy [+W]

Related Strategies¶

• Use dynamic user models to recognize non-optimal learning behaviors and redirect students toward more effective behaviors
• Adaptive Learning

Examples¶

-

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