Exploring the acceptance of virtual reality training systems among construction workers: a combined structural equation modeling and artificial neural network approach

Front Public Health. 2024 Dec 18:12:1478615. doi: 10.3389/fpubh.2024.1478615. eCollection 2024.

Abstract

Virtual Reality Training System (VRTS) has been verified effective in safety training in the construction field. However, in China, it is not widely used as a regular training tool. Among all the reasons, the acceptance level of construction workers (CWs) has the decisive impact on the promotion of VRTS. In view of this, this study is devoted to constructing a training model of CWs' acceptance level of VRTS training that integrates the technology acceptance level model with the theory of planned behavior. What's more, this paper innovatively introduces three crucial elements of external influences, namely, risk perception (RP), safety climate (SC) and self-efficacy (SE). In order to more accurately figure out the linear and nonlinear relationship between every structure and the factors of CWs' acceptance level, 528 participating CWs in this study filled in structured questionnaires, through the data of which the analyzing process uses structural equation model and artificial neural network two-stage analysis method. Based on the analyzing results of the study, this paper put forward a series of specific strategies and suggestions to significantly promote the acceptance level of CWs to VRTS training considering the designment, the enterprises and the government.

Keywords: artificial neural network; construction workers; technology acceptance model; theory of planned behavior; virtual reality training system.

MeSH terms

  • Adult
  • China
  • Construction Industry*
  • Female
  • Humans
  • Latent Class Analysis
  • Male
  • Middle Aged
  • Neural Networks, Computer*
  • Occupational Health
  • Self Efficacy
  • Surveys and Questionnaires
  • Virtual Reality*

Grants and funding

The author(s) declare that financial support was received for the research, authorship, and/or publication of this article. The National Natural Science Foundation of China #51774149 and Social Science Foundation of Jilin Province #2022B85 supported this work.