Score prediction method based on multi-source user comments

Abstract

The invention provides a score prediction method based on multi-source user comments, and belongs to the field of recommendation systems. The method includes: performing data preprocessing on the historical consumption record of the user; calculating the similarity between different users according to the user-article scoring matrix and a similarity formula, and supplementing the user comments byusing the related comments written by the similar users with the highest similarity; extracting comment features; and finally performing comment feature fusion processing. According to the invention,related comments written by similar users can be screened out based on historical consumption records of the users; according to the method, the user comments are supplemented, and the user comment supplementing document is constructed for each user, so that the problem of data sparsity of the user comments can be relieved, user portraits are enriched, the accuracy of score prediction is improved,and the satisfaction degree of the users on a recommendation system is further improved. Besides, the user comment supplementary document is composed of related comments written by similar users, andhas a certain difference from the comments written by the users themselves, so that the recommendation diversity can be improved.

Description

technical field [0001] The invention belongs to the field of recommendation systems, in particular to a rating prediction method based on multi-source user comments. Background technique [0002] In today's Internet information overload situation, information consumers without clear needs want to find interesting content conveniently, and information producers want to push their content to suitable target users, and recommendation systems have emerged as the times require. Score prediction is a classic model in the recommendation system. The system predicts the score of all items that the user has not consumed, and then recommends the N items with the highest predicted scores to the user. At present, the most widely used method in the rating prediction problem is the collaborative filtering algorithm. The collaborative filtering algorithm uses user behavior data to mine the interests of users and recommend items that may be of interest to them. Classical work includes Matrix...

AI Technical Summary

Problems solved by technology

However, since the vast majority of users are unwilling to write comments to share their consumption experience, even if some users write comments, most of them are relatively short, so the user comments themselves are sparse, and the comments of most users cannot fully represent a user’s like

Images