Exploring customer experiences and sentiments in Chinese glamping realities: A machine learning approach

Abstract

As a sustainable tourism trend blending luxury and nature, glamping has recently experienced a sharp rise in popularity. Extant literature investigates factors contributing to service quality of glamping but lacks comprehensive insights into glampers’ experiences and underlying sentiments. Based on the Experience Economy (4 Es) Framework, this study analyzes 14,201 online reviews from 20 Chinese glamping sites using machine learning techniques. Through the Latent Dirichlet Allocation (LDA) topic modeling, we identified eight key topics of the glamping experience: nature-based, service-based, family and education, accommodation, food, interaction, facility, and emotion. These dimensions align with the 4 Es framework, demonstrating its relevance in the glamping context. Sentiment analysis using SnowNLP reveals that glampers exhibit predominantly positive sentiments toward glamping, with service, hotel, and staff members evoking the strongest sentiments—both positive and negative. Negative sentiments often relate to room, hotel, service, breakfast and cleanliness, while dimensions such as service, children, original ecology, hotel, and environment inspire highly positive responses. This study represents the first comprehensive exploration of experiences and customer sentiments within the context of Chinese glamping. By developing a framework to delineate the mechanisms behind glamping experiences from an oriental perspective, this study extends the application of the 4 Es framework in the glamping field. The application of machine learning techniques addresses limitations of traditional survey methods by effectively capturing diverse attributes influencing tourist satisfaction. Besides, the study offers valuable practical insights for enhancing service quality and tailoring glamping experiences to better meet customer needs.