Evaluating cruise user satisfaction through online reviews: a method based on sentiment analysis and large-scale group decision-making
摘要
Online reviews of cruise tourism, as user-generated information, contain customers’ evaluations of various aspects of the cruise tourism industry. They influence the development of this industry by affecting potential users’ purchasing decisions. To promote the sustainable development of the cruise tourism industry, it is crucial to understand the factors influencing high user satisfaction and to ensure high levels of user satisfaction. With a focus on the factors influencing the cruise travel experience, this paper proposes a method for determining user requirements (URs) and evaluating user satisfaction with cruise tourism by integrating online review analysis with large-scale group decision-making (LSGDM). First, we establish a sentiment dictionary for the cruise domain based on online reviews, selecting seed sentiment words according to word frequency and expanding them using the Word2vec and semantic orientation using pointwise mutual information algorithms. Second, we use the latent Dirichlet allocation topic model to analyze online reviews and identify the 10 URs that are of actual concern to cruise customers. Then we perform dependency syntax analysis to conduct a fine-grained sentiment analysis of each review to identify the sentiment intensity values toward different cruise URs. Third, we evaluate the final satisfaction and ranking of URs using the LSGDM method, which includes a consensus model with a personalized feedback mechanism based on the minimum adjustment cost. We conclude by providing suggestions for improving the cruise tourism experience.