Literature Recommendation Algorithm Based on User Preference Model

Abstract

With the passage of time, literary works are becoming richer and richer in both quantity and variety, and are loved by readers. With the development of network communication technology and the continuous expansion of Internet information resources, information overload is becoming more and more serious. In the era of personalized network, resource service platform is required to actively analyze user behavior, discover user interests and preferences, and find information resources that meet their individual needs for users. In order to solve the problem of increasing number and category of literary works, the recommendation algorithm came into being. In the process of recommendation, finding the similarity between users is the key to accurate recommendation, so user preference modeling is particularly important. It is of great significance to study the modeling method of network users' preferences and the recommendation algorithm based on preference model for better providing information services for users. With the rise of social network research, many researchers combine social network with personalized recommendation to solve the problems of data sparsity, “cold start”, model scalability and robustness in traditional recommendation, which effectively improves the scalability and accuracy of recommendation. At present, there are many kinds of personalized recommendation technologies, among which content-based personalized recommendation technology and collaborative filtering recommendation technology are two common technologies. These algorithms are introduced and used by various websites to make targeted recommendations according to the characteristics of readers and books. This effect is far better than the previous pure search algorithms. This paper proposes a literature recommendation algorithm based on user preference model. This algorithm includes: Collaborative Filtering Recommendation Algorithm and memory based collaborative filtering recommendation algorithm. Then recommend books in the divided community.