Personalized tourism product design focused on tourist expectations and online reviews: An integrated MCDM method

The key to the success of tourism product design is meeting the personalized demand of consumers. This study aims to develop a personalized travel product design method that considers tourist expectations and online reviews. The method has three stages: (1) Obtaining tourist expectations of different tourism product attributes. A multi-objective optimization model is constructed to maximize tourist expectation, minimize non-traveling time, and minimize monetary cost. The non-dominated sorting genetic algorithm with an elite strategy (NSGA-II) is used to solve the model, and the obtained Pareto optimality is regarded as the set of alternative tourism products. (2) Extracting similar tourism products and their online reviews from multiple tourism websites. Tourists’ perceived value of similar tourism products is calculated through the Convolutional Neural Network (CNN). (3) Calculating customer’s expected perceived value of each alternative tourism product based on the Case-Based Decision Theory (CBDT). The optimal personalized tourism product is selected based on the customer’s expected perceived value. Finally, a case study of personalized tourism product design for a company’s group travel is given. The result indicates that the proposed method can provide a new approach for tourism companies to design personalized tourism products that meet customer demands.