Primary supervisor
Tongguang LiLeveraging the FLoRA adaptive learning platform, we will conduct a five-phase research program combining experimental studies and advanced trace data analysis. Through time-stamped interaction data, we aim to detect behavioural signals of metacognitive disengagement using machine learning and time-series modeling techniques. These insights will inform the development of adaptive scaffolding tools that encourage students to monitor, evaluate, and adjust their learning strategies when using GenAI.
Student cohort
Aim/outline
This study aims to investigate how targeted scaffolds (i.e., personalized and automated instruction) can mitigate the over-reliance on GenAI tools in higher education. Given the growing trend of students using GenAI without critically engaging with the generated content, the project will explore how metacognitive laziness manifests in real learning contexts and how scaffolds can be designed to re-engage students in self-regulated learning (SRL) processes. Specifically, the research seeks to (1) identify behavioural signals of metacognitive disengagement (i.e., observable patterns such as a lack of monitoring or questioning of GenAI outputs) when using GenAI, and (2) design, implement, and evaluate scaffolding interventions that promote metacognitive awareness and regulation during GenAI-supported tasks. The ultimate goal is to support students in cultivating self-regulation skills in the age of AI, while enabling them to meaningfully benefit from AI-assisted learning.
Required knowledge
This interdisciplinary project integrates expertise from educational technology, learning analytics, and data science to produce scalable, evidence-based tools that foster SRL.