Unpacking customer feedback and brand equity dynamics in the hospitality industry through machine learning techniques

This study utilises Latent Dirichlet allocation (LDA) and latent semantic analysis (LSA) for advanced topic modelling in the hospitality sector, analysing customer feedback from Booking.com in Ho Chi Minh City, Vietnam. It highlights crucial aspects influencing brand equity: ambient noise levels, room standards, facility provisions, staff interactions, and strategic location advantages. Further, the research integrates an extensive suite of machine learning (ML) and deep learning (DL) techniques, including logistic regression (LR), random forest (RF), multinomial Naive Bayes (NB), long short-term memory (LSTM), convolutional neural network (CNN), and notably, the dense model. The dense model stands out, demonstrating remarkable performance with an accuracy rate of 0.95 and an F1-score of 0.97, validating the effectiveness of data-driven methodologies in extracting nuanced customer sentiments. These insights offer a multifaceted understanding, serving as a valuable resource for practitioners to refine service strategies, elevate customer satisfaction, and strengthen market presence.