VR-based Silent Reading and Rosenberg Tests: Machine-Learning Approach to Identify Learning Disorders
Michele Materazzini, Gianluca Morciano, José Manuel Alcalde-Llergo, Enrique Yeguas-Bolívar, Andrea Zingoni, Juri Taborri · 2024
This study explores the intersection of self-esteem assessment, specific learning disorders (SLDs), and emerging technologies, particularly virtual reality (VR) and machine learning (ML). Through this scope, the research involved the development of novel VR-based tools for administering silent reading and Rosenberg tests, designed to simulate real-world academic challenges and social interactions. A sample of 40 Italian university students, including those diagnosed with SLDs and a control group, participated in the study. Data collected from VR were analyzed using ML algorithms, with a focus on dyslexia detection. The findings underscored the critical role of self-esteem in academic performance and overall well-being for individuals with SLDs. ML models, particularly support vector machines (SVM), demonstrated efficacy in identifying dyslexic tendencies based on data from VR. This multidisciplinary approach contributes to advancing personalized intervention strategies for individuals with SLDs, emphasizing early diagnosis and targeted support systems.