Abstract
Medical tourism is increasing quickly since it contributes to both the health and tourism sectors. The use of big social data has been effective in the development of medical tourism as a huge amount of data is produced and shared by travelers about the services through different social media platforms. Indeed, communicative infor-mation and knowledge can be mined from a large amount of information provided by travelers about medical tourism services. It is important to analyze such data to understand the customers' satisfaction level and their demands. Although several studies have been conducted to find the factors influencing customer satisfaction in medical tourism, there is a lack of studies about big social data and online behavioral analysis of medical travelers. In addition, the analysis of customers' online reviews is fairly unexplored by machine learning tech-niques in the context of medical tourism. Hence, this research aims to fill this gap and develop a new method to reveal travelers' choice preferences and satisfaction with medical tourism services through the analysis of the online review. Text mining and ontology approaches are used in the proposed method. The method can mine data from medical tourism websites, discover the satisfaction dimensions, and reveal the satisfaction level of medical tourists through textual reviews. We rely on the demographic information of medical tourists and ontological semantic filtering approaches to better detect the travelers' preferences in medical tourism websites. The proposed method is evaluated through the numerical and textual reviews obtained from medical tourism websites. The results of data analysis showed that the proposed method is effective for big data analysis in the medical tourism context and may help medical tourism organizers to improve their medical tourism services to obtain a high level of medical travelers' satisfaction.