Design Knowledge for Virtual Learning Companions from a Value-centered Perspective

Abstract

The increasing popularity of conversational agents such as ChatGPT has sparked interest in their potential use in educational contexts but undermines the role of companionship in learning with these tools. Our study targets the design of virtual learning companions (VLCs), focusing on bonding relationships for collaborative learning while facilitating students’ time management and motivation. We draw upon design science research (DSR) to derive prescriptive design knowledge for VLCs as the core of our contribution. Through three DSR cycles, we conducted interviews with working students and experts, held interdisciplinary workshops with the target group, designed and evaluated two conceptual prototypes, and fully coded a VLC instantiation, which we tested with students in class. Our approach has yielded 9 design principles, 28 meta-requirements, and 33 design features centered around the value-in-interaction. These encompass Human-likeness and Dialogue Management, Proactive and Reactive Behavior, and Relationship Building on the Relationship Layer (DP1,3,4), Adaptation (DP2) on the Matching Layer, as well as Provision of Supportive Content, Fostering Learning Competencies, Motivational Environment, and Ethical Responsibility (DP5-8) on the Service Layer.