An interpretable recommendation method integrating user implicit article preferences and implicit trust

Abstract

The invention discloses an interpretable recommendation method integrating user implicit article preference and implicit trust, and aims to solve the problems of sparse scoring data and cold start ofa recommendation system, and by mining the implicit article preference and implicit trust of a user by utilizing user comments, the accuracy and interpretability of scoring prediction can be greatly improved. According to the method, user aspect preferences and article aspect quality are mined in comments by utilizing a topic model LDA and an aspect matrix decomposition model AMF, implicit articlepreferences of a user are captured by utilizing the user aspect preferences and the article aspect quality, and implicit trust of the user is captured through user scoring and comments. And finally,the predicted score is corrected according to the implicit article preference of the user and the implicit trust of the user, so that the recommendation accuracy and interpretability can be improved.

Description

technical field [0001] The present invention designs an item recommendation method, specifically an interpretable recommendation method that integrates user implicit item preference and implicit trust. Background technique [0002] With the rapid development of Internet technology in recent years, recommendation systems have been applied to all aspects of our lives. For example: in daily online shopping, e-commerce websites such as Taobao, Jingdong, and Dangdang often recommend items of interest to users. When browsing news every day, some news platforms, such as Jinri Toutiao and Yidian News, will recommend interesting news information to users from thousands of news. Some music platforms, such as Netease Cloud Music, will recommend an exclusive playlist for users based on their music listening records. [0003] Personalized recommendation system has become an indispensable and important part of network applications, and personalized recommendation system is divided into ...

AI Technical Summary

Problems solved by technology

The first problem is: Regarding why items are recommended to users, using user ratings to explain the recommendation results is not convincing and credible

For example, if a user gives two movies 5 points at the same time, it does not necessarily mean that the user has the same emphasis on the two movies. The user may like the director of the first movie and the second movie. scenario, so both are given the same score, so the recommendation results cannot be explained solely based on user ratings

The second problem is that the information use

Images