Facilitating Online Self-Regulated Learning and Social Presence Using Chatbots: Evidence-Based Design Principles

Abstract

In an online learning environment, both instruction and assessments take place virtually where students are primarily responsible for managing their own learning. This requires a high level of self-regulation from students. Many online students, however, lack self-regulation skills and are ill-prepared for autonomous learning, which can cause students to feel disengaged from online activities. In addition, students tend to feel isolated during online activities due to limited social interaction. To address these challenges, this study explores the use of chatbots to facilitate students’ self-regulated learning strategies and promote social presence to alleviate their feelings of isolation. Using a two-phase mixed-methods design, this study evaluates students’ behavioral engagement, perceived self-regulated learning strategies, and social presence in chatbot-supported online learning. In the first phase (Stage I Study), 39 students engaged in a goal-setting chatbot activity that employed the SMART framework and social presence indicators. The findings served as the basis for improving the chatbot design in the second phase (Stage II Study), in which 25 students interacted with the revised chatbot, focusing on goal-setting, help-seeking, self-evaluation, and social interaction with instructor's presence. The results show that the students in both studies had positive online learning experiences with the chatbots. Follow-up interviews with students and instructors provide valuable insights and suggestions for refining the chatbot design, such as chatbots for ongoing monitoring of self-regulation habits and personalized social interaction. Drawing from the evidence, we discuss a set of chatbot design principles that support students’ self-regulated learning and social presence in online settings.