Research on Personalized Tourist Attraction Recommendation based on Tag and Collaborative Filtering

Tourists face a large number of tourist attractions, and spend a considerable amount of time and energy to select satisfactory tourist attractions. The application of personalized recommendation technology is an effective way to solve this problem. On the one hand, users' consumption frequency in tourism is much lower than other commodities such as music and movies; on the other hand, the increasing number of tourist attractions has led to the problem of sparse scoring data in personalized recommendations of tourist attractions. The traditional collaborative filtering algorithm is not satisfactory in the recommendation of tourist attractions. This paper builds a tourist attraction tag system, which links tourists and tourist attractions through the attractions tag from four aspects: location, location type, travel time, and travel method. By calculating the relationship between tourists and attractions tags, tourist attractions and attractions tags, a user interest model is constructed. Then, according to the user interest model, the interest degree of the new attraction to be recommended is predicted, and finally the tourist attraction recommendation set is generated.