WCSE

Collaborative Recommendation of Tourist Attractions Based on the Comprehensive Similarity of Users

Abstract— One problem in collaborative filtering recommendation is the sparseness of the rating data, which affects the quality of system recommendations. We propose a new method which uses the similarity of the image formed by the user's personality tags, the similarity of the user's historical rating records, and the similarity of the attention among friends to make up for the lack of calculating similarity using only rating data. The three similarities are multiplied by their respective weights and combined to obtain a comprehensive similarity for prediction. The experimental results show that the improved similarity method can better distinguish the similarity between users and users, effectively improve the accuracy of neighbor selection, reduce the average absolute error between the predicted score and the actual score, and improve the accuracy of the score prediction

Index Terms—Rating prediction, collaborative filtering, user personality tag, Friend attention, recommendation algorithm, similarity

Jinlong Chen, JiaLing Li
Guangxi Key Laboratory of Cryptography and Information Security , Guilin University of Electronic Technology, CHINA
Guangxi Key Laboratory of Trusted Software , Guilin University of Electronic Technology, CHINA

[Download]

Cite:Jinlong Chen, JiaLing Li, "Collaborative Recommendation of Tourist Attractions Based on the Comprehensive Similarity of Users " Proceedings of 2020 the 10th International Workshop on Computer Science and Engineering (WCSE 2020), pp. 239-245, Shanghai, China, 19-21 June, 2020.