Fostering Diagnostic Decision-Making in Special Education Students through Simulation-Based Games and AI Pedagogical Agents: A Case-Based Learning Comparison in Higher Education

Abstract

Educational diagnostic skills are essential in special education, both for identifying students’ special needs and for making informed pedagogical decisions in daily practice. Simulation-based learning presents a promising approach in higher education by connecting theoretical knowledge to real-world problems and enabling in-depth analysis of diagnostic processes through the generation of data. This study examines the use of simulations in diagnostic case processing, comparing two formats: a digital structured click game and a discursive interaction with an AI-based Pedagogical Agent (PA). Both games were developed for students with special education needs who possess expertise in diagnostic processes.
Findings indicate that both interactive learning environments effectively support the development of diagnostic skills and processes. All participants successfully completed the games, although 75% required additional support during the AI conversation. Participants demonstrated significantly varying levels of efficiency and accuracy in their diagnostic process across the two games. This paper explores the underlying reasons for these differences and discusses the potential benefits and limitations of interactive learning environments, with and without AI integration.