Supporting Self-Regulated Learning Using Pedagogical Agents With an Intelligent Tutoring System

• In Event: Using Multimodal Trace Data to Support Learners Across Tasks and Contexts

Abstract

Objectives. Supporting self-regulation through adaptive scaffolding delivered by pedagogical agents (PAs) during learning with intelligent tutoring systems (ITS) and other advanced learning technologies is of critical importance. Using Winne’ (2018) theoretical perspective on self-regulated learning (SRL) and extensive empirical research on scaffolding SRL with ITSs such as MetaTutor we designed and tested the effectiveness of PAs to scaffold students in regulating their own learning about human biology with MetaTutor (Azevedo et al., 2022; Taub et al., 2021). We converged product data with several on-line measures of cognitive, affective, and metacognitive processes to test the effectiveness of scaffolding with (i.e., the adaptive version of MetaTutor) or without the PAs (i.e., the non-adaptive version of MetaTutor).

Method and Data Sources. 120 undergraduates participated in a 2-day experiment with MetaTutor to learn about the human circulatory system. They were instructed to use several key SRL processes during their learning session. Participants were randomly assigned either to the adaptive or non-adaptive condition. The effectiveness of PAs’ metacognitive scaffolding was assessed based on analyses of participants’ 2-hour session with MetaTutor where we collected the following data from each participant: eye tracking, video recording of the face (for affect detection), log files (e.g., metacognitive judgments, learner-agent dialogue), and notes. We also collected pretest and posttest data and several self-report measures on agent likeability and metacognitive knowledge about specific SRL processes, and motivational traits (e.g., self-efficacy).

Results. Results indicated statistically significant differences between MetaTutor conditions (p < .05), such that learners in the adaptive scaffolding condition had higher learning gains and sub-goal quiz scores, spent more time engaging in each learning sub-goal, engaged in more help-seeking behavior from the PAs, inspected more relevant and less irrelevant multimedia materials during learning, deployed more sophisticated learning strategies, and made higher metacognitive judgments, compared to participants in the non-adaptive condition. These results suggest the importance of adaptive scaffolding on learning about complex topics and promoting the effective use of SRL strategies while interacting with ITSs.

Scientific and Educational Significance. Affording learners opportunities to be scaffolded by PAs acting as external regulating agents is effective in fostering learning and self-regulated learning. In addition, multimodal data sources provide evidence that has the potential to advance current conceptual, theoretical, methodological, and analytical frameworks related to scaffolding and SRL, based on self- and external regulation.

Authors

• Roger Azevedo, University of Central Florida
  Presenting Author

• Daryn Dever, University of Central Florida
  Non-Presenting Author

• Megan Wiedbusch, University of Central Florida
  Non-Presenting Author

• Saerok Park, University of Central Florida
  Non-Presenting Author

• David Alejandro Organista, University of Central Florida
  Non-Presenting Author