Studying Self-Regulatory Processes Using Multimodal Trace Data: What Does the Evidence Reveal?

• In Event: What Can Multimodal Data Streams Reveal About Students’ Self-Regulated Learning?

Abstract

Understanding the complex nature of cognitive, affective, metacognitive, and motivational (CAMM) processes during learning with advanced learning technologies (ALTs) is key to understanding how these processes impact learning about complex topics. Current methodological and analytical approaches to studying SRL processes (e.g., self-reports) have several weaknesses compared to capturing real-time deployment of SRL processes. Our approach has been to use MetaTutor (an intelligent, hypermedia multi-agent ALT) to collect rich multimodal multichannel trace data of CAMM processes during learning (e.g., eye tracking, facial expressions of emotion). In this presentation, we focus on the challenges in measuring, analyzing, and inferring temporally unfolding CAMM self-regulatory processes using multichannel, multimodal data (collected from several studies with undergraduates) during human-machine interactions with MetaTutor.

Authors

• Roger Azevedo, North Carolina State University

• Michelle Taub, North Carolina State University

• Nicholas Vincent Mudrick, North Carolina State University

• Amanda Bradbury, North Carolina State University

• Megan Price, North Carolina State University