The Role of Conversational Agents for Supporting Self-Regulated Learning in Modern Learning Environments

• In Event: Differential Learning Formats for Self-Regulated Learning

Abstract

Purpose
The purpose of this presentation is to discuss the creation of Conversational Agent (CA) skills that support student access to high-quality instruction in learning environments that extend beyond the traditional classroom. The presenters will outline essential components based on self-regulated learning (SRL) theories to support the design and creation of CA skills, which can be accessed by students through ubiquitous smart home speakers and other voice-capable devices.
Theoretical Framework
Well-designed CA skills can simulate effective student-teacher interactions where students engage and interact with the digital personal CA to receive personalized learning support, guidance, and feedback. SRL provides an avenue to understand individual learners’ cognitive, motivational, and emotional aspects of learning (Panadero, 2017). Effective learning occurs in a structured learning environment that minimizes the impact of cognitive load by supporting learners in developing SRL skills (Kirschner, 2002). With support, students can utilize SRL skills to better allocate cognitive resources to the learning tasks (Park et al., 2015). CAs can provide prompts for students to SRL activities toward solving problems, when immediate teacher guidance is absent in environments (Carter et al., 2021). This presentation will discuss designing CA skills guided by SRL theories (Pintrich, 2000; Winne & Hadwin, 1998; Zimmerman, 2008).
Techniques and Materials
Building a CA starts with creating a dialogue flow, which is a script illustrating the conversation between the learner and the CA. Given learner variability, designers of CAs are suggested to consider all supports needed for all learners to succeed in learning experiences. CA can guide individual learners through instruction step by step. Compared to traditional f2f settings, the individual guidance process provided by technology can be embedded with more opportunities for learners to practice self-regulation skills.
Design Features
Embedding SRL support within CA skills is guided by Zimmerman’s (2000) cyclical model, which include three phases: forethought, performance, and self-reflection. In the forethought phase, learners engage in task analysis (e.g., goal setting, strategic planning) and activation of motivational beliefs that influence the use of learning strategies. In the performance phase, learners perform the task, use self-control strategies, and monitor their progress. In the self-reflection phase, learners self-evaluate how they have performed the task and make attributions of performance to perceived causes. Learners generate self-reactions, such as self-satisfaction and adaptive or defensive responses that can positively or negatively influence future task performances. Table 1 shows how SRL phases guide the design of multiple key components of CA skills that support personalized learning for students.
Significance
CAs have the potential to capture myriad variables related to student engagement and learning in ever-changing environments. These variables can include student learning progress, performance, and preferences, which can be used to support student learning and self-regulation any time, any place. The design considerations for CA skills discussed in the presentation will advance scientific knowledge in using CA as an innovative solution that integrates functionalities of voice technologies and learning theories to support students with diverse learning needs.

Author

• Richard A. Carter, University of Wyoming
  Presenting Author