Scholarlink

<p>The rapid digital transformation of the global economy demands continuous workforce reskilling and upskilling to meet evolving technological needs. While immersive technologies such as 360-degree Virtual Reality (VR) are increasingly integrated into industrial training, limited research has addressed the behavioral mechanisms underlying their adoption. This study bridges that gap by integrating the Unified Theory of Acceptance and Use of Technology (UTAUT) with VR-specific constructs—interaction, immersion, and imagination—to examine behavioral intention to adopt a 360-degree Virtual Smart Factory Laboratory. Data from 307 participants, including engineering students and technicians, were analyzed using Partial Least Squares Structural Equation Modeling (PLS-SEM). Results show that performance expectancy and social influence significantly affect behavioral intention, while immersion and interaction influence performance and effort expectancy. To further explore and validate key drivers, three feature importance methods—SHapley Additive Explanations (SHAP), Random Forest, and Permutation Importance—were compared. All three techniques consistently ranked social influence and performance expectancy as the most influential predictors, while immersion and interaction showed lower but supportive contributions. This multi-method comparison enhances the robustness of the analysis and offers interpretable, ranked insights into predictive relevance. The findings inform the design of more effective, user-centered VR training systems that support workforce development and digital transformation.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A hybrid machine learning framework for explaining VR360 smart factory training adoption

  • 期刊论文

  • 发表日期：

    2026年3月27日

查看全文
  • Rattawut Vongvit,
  • Anyapat Kongwattananan

摘要

The rapid digital transformation of the global economy demands continuous workforce reskilling and upskilling to meet evolving technological needs. While immersive technologies such as 360-degree Virtual Reality (VR) are increasingly integrated into industrial training, limited research has addressed the behavioral mechanisms underlying their adoption. This study bridges that gap by integrating the Unified Theory of Acceptance and Use of Technology (UTAUT) with VR-specific constructs—interaction, immersion, and imagination—to examine behavioral intention to adopt a 360-degree Virtual Smart Factory Laboratory. Data from 307 participants, including engineering students and technicians, were analyzed using Partial Least Squares Structural Equation Modeling (PLS-SEM). Results show that performance expectancy and social influence significantly affect behavioral intention, while immersion and interaction influence performance and effort expectancy. To further explore and validate key drivers, three feature importance methods—SHapley Additive Explanations (SHAP), Random Forest, and Permutation Importance—were compared. All three techniques consistently ranked social influence and performance expectancy as the most influential predictors, while immersion and interaction showed lower but supportive contributions. This multi-method comparison enhances the robustness of the analysis and offers interpretable, ranked insights into predictive relevance. The findings inform the design of more effective, user-centered VR training systems that support workforce development and digital transformation.