Artificial Intelligence Enhanced Integration of Art Education and Cultural Tourism for Student Engagement Improvement through PLS-SEM and IPMA

Abstract

This study examines the impact of integrating art education with cultural tourism through Artificial Intelligence (AI) applications, with a particular focus on how this integration influences student engagement. Data were collected from 243 undergraduate art students in China to support the analysis. Based on engagement theory, a conceptual framework was developed to investigate the contributions of behavioral, cognitive, and emotional engagement in shaping students' willingness to participate in AI-enhanced cultural learning experiences. The core AI system is implemented using a feedforward neural network architecture, in which output values are computed by applying a nonlinear activation function to weighted inputs and bias terms. To assess the data, the research applied Partial Least Squares Structural Equation Modeling (PLS-SEM) and Importance-Performance Map Analysis (IPMA). Findings reveal that emotional engagement exerts the strongest influence on engagement intention, followed by cognitive and behavioral engagement with decreasing levels of impact. IPMA results further confirm that emotional engagement is the most critical dimension in terms of both importance and performance. These findings underscore the significance of AI-driven personalized cultural experiences and adaptive content delivery, demonstrating how neural networks can be effectively utilized to foster emotionally immersive learning environments in higher education.