Bridging the Gap: Exploring the Factors Influencing Student Involvement and Competency Development in College Instruction Utilizing Virtual Reality

Abstract

Despite heavy investments and its popularity in tertiary education,  quantitatively predicting student Knowledge Retention remains a major challenge and to determine which technical and experiential variables, however, could significantly impact learning performance in these complex, immersive settings. The rapid uptake of Virtual Reality (VR) in higher education demands a powerful analytics-based framework to assess VR’s impact. This work fills the critical gap in predictive modeling by focusing on how the main factors for Knowledge Retention are captured and analyzed in the VR college teaching environment. The underlying objective was to build and validate a powerful machine learning (ML) model, and identify the important operational and psychological factors influencing student learning outputs. We utilized a large dataset (VR_College_Teaching_Dataset.csv) where variables such as student engagement, technical performance (e.g., Lag_Time, System_Usage), and psychological variables (e.g., Satisfaction_Score, User Feedback) were involved. We conducted an ML comparison of five different algorithms (Neural Network, Ensemble, Decision Tree, Forest, and Gradient Boosting). We picked the Neural Network model because this one had the strongest predictive precision on the test partition, with 225.4834 Average Squared Error which is the minimum average squared error of any model. Features importance analysis revealed a less clear feature hierarchy. The Satisfaction_Score of the student was the strongest predictor’s of Knowledge Retention, which was complemented by Lag_Time, as a technical metric, with the next mos important factors User_Feedback and System Usage. Such an important discovery is that high retention of knowledge in a deep-immersive VR learning system does not only depend on the content or duration, and  that it is mediated by the psychological experience of the student (satisfaction) and the functioning of the technical 26 a college-level VR educational context. These results demonstrate that correlation and predictive modeling system used (little latency/lag). The established framework provides essential and evidence-based suggestions for educational technologists that promote the effective technical delivery and the optimum user experience, which are aimed at the successful pedagogical deployment of VR in the academic ecosystem.

How to cite this article:
Beg M S. Bridging the Gap: Exploring the
Factors Influencing Student Involvement and
Competency Development in College Instruction
Utilizing Virtual Reality. J Adv Res Lib Inform Sci
2026; 13(2): 25-29.

DOI: https://doi.org/10.24321/2395.2288.202609