The Power of Nudging: Exploring Three Interventions for Metacognitive Skills Instruction across Intelligent Tutoring Systems

TL;DR

This study investigates three intervention strategies to improve metacognitive skills in students using intelligent tutoring systems, demonstrating that nudging significantly enhances strategy use and learning outcomes.

Contribution

It introduces and evaluates three novel interventions for teaching strategy selection in intelligent tutoring systems, highlighting the effectiveness of nudging in metacognitive skill development.

Findings

Nudge intervention outperformed default strategies.

Nudge students caught up with StrTime students.

Interventions improved strategy use and learning outcomes.

Abstract

Deductive domains are typical of many cognitive skills in that no single problem-solving strategy is always optimal for solving all problems. It was shown that students who know how and when to use each strategy (StrTime) outperformed those who know neither and stick to the default strategy (Default). In this work, students were trained on a logic tutor that supports a default forward-chaining and a backward-chaining (BC) strategy, then a probability tutor that only supports BC. We investigated three types of interventions on teaching the Default students how and when to use which strategy on the logic tutor: Example, Nudge and Presented. Meanwhile, StrTime students received no interventions. Overall, our results show that Nudge outperformed their Default peers and caught up with StrTime on both tutors.