"How do metacognitive processes dynamically adapt across diverse educational contexts, and what role do individual differences play in this adaptation?"
Investigating how students develop, deploy, and refine self-regulation strategies in digital learning environments, with particular attention to the complex interplay between cognitive, metacognitive, and motivational factors.
"How can we leverage Large Language Models to analyze educational data at scale while maintaining theoretical integrity and pedagogical relevance?"
Developing theoretically-grounded frameworks for using LLMs to analyze complex educational data, including student reflections, learning behaviors, and interaction patterns, to create more responsive and personalized learning experiences.
"What temporal patterns of engagement predict successful learning outcomes, and how do these patterns vary across different learner populations?"
Applying advanced data science methods to identify meaningful patterns in educational data, focusing on time-based analytics and behavioral sequences that differentiate successful learning trajectories from less effective ones.
"How can we develop more sensitive methodological approaches to detect heterogeneous treatment effects in educational interventions?"
Advancing statistical methodologies for causal inference in educational research, particularly developing novel approaches for examining moderation effects and heterogeneous treatment impacts across diverse student populations.