Evaluating eXtended Reality (XR) and Desktop Modalities for AI Education

Abstract This paper is an extended version of the best paper from the HUCAPP 2025 conference. The abstract nature of Artificial Intelligence (AI) concepts presents an educational challenge. This paper compares an immersive extended reality (XR) environment to a traditional desktop setup for teaching Neural Networks and Handwritten Digit Recognition. We analyzed differences in student engagement, user experience, and learning outcomes between the two modalities. In this comparative study, 56 participants learned about AI concepts using either an XR headset (Meta Quest 3) or a desktop computer. We collected data on usability, satisfaction, immersion, and likelihood to recommend using the System Usability Scale (SUS), User Satisfaction Questionnaire (USQ), Immersion Presence Questionnaire (IPQ), and Net Promoter Score (NPS) questionnaires. Learning outcomes were assessed via multiple-choice questions administered during the lesson. The XR group reported significantly higher engagement, immersion, satisfaction, and likelihood to recommend the system. However, this increased engagement did not translate to superior learning outcomes; performance on in-lesson questions was comparable between the two groups. XR users also identified challenges, including physical discomfort and unfamiliarity with the technology. The findings suggest that XR can increase student motivation in AI education, but this does not automatically lead to better learning performance. Usability challenges and the novelty of the technology may hinder knowledge absorption. Future work should focus on scaffolding strategies to mitigate these issues and better leverage XR’s educational potential by personalizing the learning experience.