Dysregulated Learning with Advanced Learning Technologies

Successful learning with advanced learning technologies is based on the premise that learners adaptively regulate their cognitive and metacognitive behaviors during learning. However, there is abundant empirical evidence that suggests that learners typically do not adaptively modify their behavior, thus suggesting that they engage in what is called dysregulated learning. Dysregulated learning is a new term that is used to describe a class of behaviors that learners use that lead to minimal learning. Examples of dysregulated learning include failures to: (1) encode contextual demands, (2) deploy effective learning strategies, (3) modify and update internal standards, (4) deal with the dynamic nature of the task, (5) metacognitive monitor the use of strategies and repeatedly make accurate metacognitive judgments, and (6) intelligently adapt behavior during learning so as to maximize learning and understanding of the instructional material. Understanding behaviors associated with dysregulated learning is critical since it has implications for determining what they are, when they occur, how often they occur, and how they can be corrected during learning. The Importance of Self-Regulated Learning Successful learning with advanced learning technologies is based on the premise that learners adaptively regulate their cognitive and metacognitive behaviors during learning (Aleven et al. in press; Azevedo et al. in press a; Winne, in press). However, there is abundant empirical evidence that suggests that learners typically do not adaptively modify their behavior, thus suggesting that they engage in what is called dysregulated learning. Dysregulated learning is a new term that is used to describe a class of behaviors that learners use that lead to minimal learning. Examples of dysregulated learning include failures to: (1) encode contextual demands (e.g., retain an internal mental representation of the hierarchical structure of the instructional materials), (2) deploy effective learning strategies (e.g., note-taking and knowledge elaboration), (3) modify and update internal standards, (4) deal with the Copyright © 2010, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved. dynamic nature of the task (e.g., internalize and correct behavior based on the system’s feedback and scaffolding), (5) metacognitive monitor the use of strategies and repeatedly make accurate metacognitive judgments, and (6) intelligently adapt behavior during learning so as to maximize learning and understanding of the instructional material. Understanding behaviors associated with dysregulated learning is critical since it has implications for determining what they are (i.e., detection and classification), when they occur (e.g., onset, duration, temporal dynamics, antecedents), how often they occur (e.g., patterns across time, maladaptivity), and how they can be corrected during learning (e.g., inference based on converging evidence, system intelligence, scaffolding, and feedback). The goal of this paper is to: (1) present MetaTutor, an adaptive intelligent multi-agent learning environments designed to train and foster students’ SRL and content understanding; (2) present empirically-based examples of dysregulated and regulated learning; and, (3) present some challenging for future directions. MetaTutor: An Adaptive Multi-Agent Hypermedia Learning Environment MetaTutor is a hypermedia learning environment that is designed to detect, model, trace, and foster students’ selfregulated learning about human body systems such as the circulatory, digestive, and nervous systems (Azevedo et al. 2009, 2010). Theoretically, it is based on a general premise of SRL as an event and on cognitive models of SRL (Pintrich 2000; Winne and Hadwin 2008; Zimmerman 2008). The underlying assumption of MetaTutor is that students should regulate key cognitive and metacognitive processes in order to learn about complex and challenging science topics. The design of MetaTutor is based on our extensive research (see Azevedo 2008; Azevedo et al. in press a; Azevedo and Witherspoon 2009) showing that providing adaptive human scaffolding that addresses both the domain knowledge and the processes of SRL enhances students’ learning science topics with hypermedia. Overall, our research has identified key self-regulatory processes 5 Cognitive and Metacognitive Educational Systems: Papers from the AAAI Fall Symposium (FS-10-01)