The Effectiveness of Pedagogical Agents’ Prompting and Feedback in Facilitating Co-adapted Learning with MetaTutor

Abstract

Co-adapted learning involves complex, dynamically unfolding interactions between human and artificial pedagogical agents (PAs) during learning with intelligent systems. In general, these interactions lead to effective learning when (1) learners correctly monitor and regulate their cognitive and metacognitive processes in response to internal (e.g., accurate metacognitive judgments followed by the selection of effective learning strategies) and external (e.g., response to agents' prompting and feedback) conditions, and (2) pedagogical agents can adequately and correctly detect, track, model, and foster learners' self-regulatory processes. In this study, we tested the effectiveness of PAs' prompting and feedback on learners' self-regulated learning about the human circulatory system with MetaTutor, an adaptive, multi-agent learning environment. Sixty-nine (N=69) undergraduates learned about the topic with MetaTutor, during a 2-hour session under one of three conditions: prompt and feedback (PF), prompt-only (PO), and no prompt (NP) condition. The PF condition received timely prompts from several pedagogical agents to deploy various SRL processes and received immediate directive feedback concerning the deployment of the processes. The PO condition received the same timely prompts, without feedback. Finally, the NP condition learned without assistance from the agents. Results indicate that those in the PF condition had significantly higher learning efficiency scores than those in both the PO and control conditions. In addition, log-file data provided evidence of the effectiveness of the PA's timely scaffolding and feedback in facilitating learners' (in the PF condition) metacognitive monitoring and regulation during learning.

Can the use of cognitive and metacognitive self-regulated learning strategies be predicted by learners’ levels of prior knowledge in hypermedia-learning environments?

“…We know that in real-world classroom settings, there are many factors that can influence learning, and so it is important to consider multiple factors when conducting (2012) engaged participants in the learning session for two hours, which can be seen to some researchers as too long, and to others as an appropriate learning time. In contrast, the MetaTutor (Azevedo et al, 2012a) learning session lasts for one hour. Shapiro (2008) suggested that many different student characteristics, such as prior knowledge, can affect the way they use hypermedia environments, for example hypermedia assisted learning.…”

“…Despite the increasing evidence for the effectiveness of self-regulated learning for students' learning outcomes , research has also revealed that students do not enact these effective self-regulated learning strategies during learning (Azevedo, 2005;Azevedo et al, 2012). Interdisciplinary researchers have been designing and developing computer-based learning environments (CBLEs) (e.g., multimedia, hypermedia, intelligent tutoring systems, multi-agent systems) to foster and promote effective self-regulated learning in students as they learn about various topics, such as biology, physics, and ecology (Aleven et al, 2010;Azevedo & Aleven, 2013;Biswas et al, 2010;Graesser et al, 2007;Jonassen & Land, 2012;D'Mello et al, 2013;Lajoie et al, 2013;Lester et al, 2013;Woolf, 2009).…”

“…Some CBLEs are multi-agent, such that they are programmed to include pedagogical agents, PAs, who are present to assist students by providing scaffolding and feedback during learning, problem solving, strategy training, and skill acquisition (Azevedo et al, 2012a;Biswas et al, 2010;D'Mello et al, 2013;Graesser & McNamara, 2010;Lester et al, 2013). In addition to content learning, these agents are programmed to assist learning about different aspects of SRL, such as planning, goal-setting, metacognitive monitoring, strategy use, and reflection (see Azevedo & Aleven, 2013;Azevedo et al, 2012).…”

“…In addition to content learning, these agents are programmed to assist learning about different aspects of SRL, such as planning, goal-setting, metacognitive monitoring, strategy use, and reflection (see Azevedo & Aleven, 2013;Azevedo et al, 2012). The use of PAs can be effective for learners because research has shown that when students are provided with the appropriate scaffolding, this can help them to better learn (Kinnebrew et al, 2013), and more specifically to self-regulate their learning (Azevedo et al, 2012a;Graesser & McNamara, 2010;Winters et al, 2008). The role of prior knowledge is a critical individual differences variable that has not been adequately examined in the context of SRL and learning with multi-agent systems.…”

Understanding and Predicting Student Self-Regulated Learning Strategies in Game-Based Learning Environments

“…For example, in MetaTutor, a hypermedia environment for learning biology, think-aloud protocols have been used to examine which strategies students use, while analysis of students' navigation through the hypermedia environment helps to identify profiles of self-regulated learners (Azevedo et al 2010). Further studies have examined the role of prompts encouraging students to set and monitor specific learning goals (Azevedo et al 2012). The results of these investigations identified the importance of providing timely prompts as well as offering feedback on students' responses to the prompt.…”