Students' Conceptual Explanations of Neural Networks Enabled by Extended Reality Learning: A Multiple Methods Approach

ABSTRACT This study examines the use of extended reality (XR) in helping students with conceptual comprehension of artificial intelligence (AI) concepts, specifically neural networks (NNs) and handwritten digit recognition. Using a multi‐methods approach, this study assesses student performance and understanding of such concepts. Student participants ( N = 29) engaged in an XR environment designed to teach NNs and completed in‐lesson assessments consisting of multiple‐choice questions and open‐ended questions. Quantitative data were analyzed using the k ‐means clustering method to classify performance levels based on the accuracy of the answers. The elbow approach determined the number of clusters, and the average silhouette score showed the cluster quality after clustering. Qualitative data underwent thematic analysis to identify challenges in handwritten digit recognition. Results showed that the accuracy of the students' responses ranged from 17% to 100% and could be classified into three groups, and that factors like handwriting clarity, digit placement, and writing style significantly impacted the accuracy of handwritten digit recognition. The findings suggest the potential of using XR for supporting learning and engagement in studying AI concepts. Future research is encouraged to apply XR across various education levels and explore broader AI concepts. This study contributes to the literature on applying XR in computer science education by providing insights into how XR can enhance conceptual comprehension of complex AI concepts like NNs.