User-based Collaborative Filtering for Tourist Attraction Recommendations

A user-based tourist attraction recommender system is developed in this paper. The recommender system is constructed as an online application which is capable of generating a personalized list of preference attractions for the tourist. Modern technologies of classical recommender system, such as collaborative filtering are considered to be effectively adopted in the tourism domain. On the basis of collaborative filtering principle, the recommendation process of tourist attractions divided into three steps, representation of user (tourist) information, generation of neighbor users (tourists) and the generation of attraction recommendations. In order to calculate the similarities between each user, the Cosine method is adopted during the process of the generation of neighbors. And then the recommendations of attractions are generated according to the visiting history of the user's neighbors. In order to demonstrate the calculation process of the system, a case is demonstrated in detail.