Digitally empowered green public services in environmentally vulnerable areas: Insights from SEM-ANN analysis

Abstract

In the context of environmentally fragile areas in China, this study employs Partial Least Squares Structural Equation Modeling (PLS-SEM) based on the Technology Acceptance Model (TAM) and Social Cognitive Theory (SCT), integrating Observational Learning and Self-Efficacy as mediator variables. Using SEM and Artificial Neural Network (ANN) cross-analysis, the research delves into how digital empowerment impacts the sustainable development of green public services. Empirical evidence suggests that green public services' perceived usefulness and ease of use substantially impact residents' intentions to adopt them, influencing their actual usage behaviour. The adoption process is significantly influenced by social influence, highlighting the importance of social networks and collective cognition. Conversely, self-efficacy partially inhibits the willingness to adopt digital empowerment, suggesting the necessity to address users' risk perceptions. This study provides theoretical insights into the dynamics of digitally enabled green public services. It offers practical implications for policymakers aiming to enhance environmental quality and sustainable development in vulnerable regions.