Research on Tourist Satisfaction of Asian Disneyland Based on Big Data and Text Analysis

Disney theme parks, created from the vibrant tapestry of animated films, characters, and their iconic stories, offer visitors a range of thrilling entertainment facilities, performing arts, culinary services, and shopping experiences, drawing numerous visitors worldwide. Currently, there are six Disney theme parks globally, with three located in Asia. A thorough understanding of visitor satisfaction within these theme parks is crucial for optimizing park operations and enhancing the quality of guest services. Leveraging big data technology allows for a comprehensive and objective insight into visitors' experiences, needs, and preferences, thereby fostering an improvement in service quality and an enhancement in visitor satisfaction. However, the majority of current research on Disney theme park visitor satisfaction relies on survey methods for data collection and analysis, presenting limitations in data breadth and the capture of visitors' multidimensional needs. To address this research gap and gain a deeper understanding of visitors' multidimensional needs and their impact on satisfaction, this paper undertakes the following study. This study initially employed Python web scraping techniques to collect user reviews of Asian Disney theme parks from online travel agencies (OTAs) such as Ctrip and TripAdvisor, and analyzed the data using ROST content mining software. Through big data and textual analysis, this research aims to delve into the determining factors of guest satisfaction in Asian Disney theme parks. The study found that factors such as the geographic location of Disney theme parks, visitor volume, facility utilization, guest interaction experiences, and service quality significantly affect visitor satisfaction. Building on this foundation, and by integrating consumer behavior theory with a deep fusion perspective of the tourism market, as well as considering external environmental variables and cross-cultural differences, this research proposes recommendations for future directions and strategies in guest satisfaction studies.