Information recommendation method, emotion tendency determination method and device and electronic device

Abstract

The embodiment of the invention provides an information recommendation method, an emotion tendency determination method and device and an electronic device. The method comprises the steps of obtainingan interactive text of a target user; analyzing the interactive text by adopting a preset text tendency analysis strategy, and determining the emotional tendency of the interactive text; according tothe emotional tendency of the interactive text, determining the emotional tendency of the target user; and according to the emotional tendency of the target user, recommending information corresponding to the emotional tendency to the target user. Therefore, by applying the embodiment of the invention, the emotional tendency of the target user is accurately determined by analyzing the emotional tendency of the target user, and the information recommendation is carried out, so that a benign interaction is formed, the emotional state of the user is improved, and the user activeness is stimulated.

Description

technical field [0001] The invention relates to the technical field of computer network-based personalized information recommendation based on user information, in particular to an information recommendation method and device, a method and device for determining user emotional tendency, and electronic equipment. Background technique [0002] With the explosive growth of information resources, many websites will recommend relevant information to users in a personalized manner based on the records of information that users have watched. [0003] Currently, personalized recommendation algorithms based on content and user portraits are common. For example, content-based recommendation algorithms, association rule-based recommendation algorithms, and collaborative filtering recommendation algorithms. [0004] The personalized recommendation algorithm based on content and user portrait is mainly based on the records of information users' existing usage data information, and recom...

AI Technical Summary

Problems solved by technology

[0005] Obviously, the personalized recommendation algorithm based on content and user portraits only recommends information related to the content they have watched based on the text content information of the data information, and does not consider whether the user’s emotional tendency when viewing information is positive, positive or negative. Neutral vs. Negative Emotional Tendency

Images