Examining the influence of user engagement on tourist virtual reality behavioral response from the human-computer interaction perspective: A PLSSEM-IMP-NN hybrid machine learning approach

Due to the impact of the COVID-19 pandemic, new attraction ways are tended to be adapted by compelling sites to provide tours product and services, such as virtual reality (VR) to visitors. Based on human-computer interaction (HCI) user engagement and domain segmentation innovativeness theory, we develop and test a theoretical framework using a hybrid partial least squares structural equation model (PLSSEM) with Importance Performance Matrix (IMP) and neural network machine learning approach (PLSSEM-IMP-NN) that examines key user engagement drivers of visitors’ attitude toward VR (ATT) and in-person tour intentions (ITI) during COVID-19. According to a sample of visitors' response, the results demonstrate that a) user engagement including aesthetic appeal, focused attention, perceived usability, and reward experience, raise attitude toward VR; b) product-possessing innovativeness positively moderates the relationships between ATT and ITI; c) information-possessing innovativeness negatively moderates the relationships between ATT and ITI; d) ATT exert the mediating effect between user engagement and ITI. The proposed new PLSSEM-IMP-NN approach has been examined and denotes its efficient and effective in HCI and behavioral response assessment. Other contributions to theories and practical implications are discussed accordingly.