Information recommendation method and system based on user viewpoints and emotional tendency

Abstract

The invention discloses an information recommendation method and system based on user viewpoints and emotional tendency, and the method comprises the steps: S1, analyzing the viewpoints and emotionaltendency of a user based on the browsing content and browsing history of the user; S2, performing viewpoint and emotional tendency analysis on the to-be-recommended information; S3, calculating a viewpoint matching degree and an emotional tendency matching degree between the user and the to-be-recommended information; and S4, recommending information to the user, and dynamically adjusting a recommendation strategy. According to the information recommendation method based on the user viewpoint and the emotional tendency, the emotional tendency of the text is considered, recommendation is more targeted, click feedback of the user to the recommendation information is considered, the recommendation strategy is dynamically adjusted, and recommendation has self-adaptability.

Description

technical field [0001] The present invention relates to an information recommendation method and system based on user views and emotional tendencies, in particular to an information recommendation method and system that can be applied to information recommendation and information guidance in the field of data mining technology. Background technique [0002] With the development of communication technology and Internet technology, the network has gradually become an important source of information for people, especially after the Internet enters the Web2. Users post texts, share photos, videos, etc. on the Internet, and the amount of network information increases exponentially, which brings about the problem of information overload. Recommendation system is one of the most effective ways to solve information overload. The existing recommendation methods are mainly divided into two types: the first one is based on content filtering, which realizes the recommendation function ...

AI Technical Summary

Problems solved by technology

When the content browsed by the user is relatively negative, the existing recommendation methods cannot recommend appropriate information to positively guide the user's emotion

This deficiency may allow bad information such as violence and rumors to spread wantonly, affecting people's lives, causing people to panic, and even endangering social stability.

Images