A Privacy-Preserving Book Recommendation Model Based on Multi-agent

Abstract

Recommendation systems are widely used to cope with the problem of information overload in digital libraries, consequently, many recommendation methods have been successfully applied in the present book recommendation systems, such as collaborative filtering, content-based, association rule mining-based and so on. But they are always lack of user's privacy concerns. Aiming at this disadvantage, in this work, a privacy-preserving book recommendation system (PPBRS) is introduced. This paper discusses the system structure of PPBRS at first. In addition, it discusses the functions of every agents and the operating process in the system. This recommendation system allows multiple recommendation methods to cooperate with one another to present their best recommendations to the user, can meet the needs of multiple recommendation, and also can protect users' privacy while providing high-quality recommendations efficiently. Finally, we give a simple review of the work accomplished and conclude further research directions of the system by analyzing the existing work.