Music recommendation method based on emotional context of microblog

Abstract

The present invention provides a music recommendation method combined with an emotional state of a user for improving music recommendation effect. The method comprises the following steps: extracting and modeling an emotional context based on an emotion dictionary; constructing a music record that comprises the emotional context; and recommending music based on the emotional context of the user. The music recommendation method provided by the present invention primarily uses microblog data issued by the user, common microblogs and music sharing microblogs included, so that music demand and preference of the user in different emotional states are obtained; and the current emotional state of the user and the music preference of the user under the emotional state during recommendation are taken into consideration, thereby making the recommended music more close to the preference of the user under the emotional state.

Description

technical field [0001] The invention relates to the field of emotion mining and recommendation systems, and mainly designs a music recommendation method based on microblog emotional context. Background technique [0002] Emotion mining is to obtain the emotional state of a specific user through some methods. The most intuitive method is to obtain various physiological data indicators of the user through some sensors such as heartbeat, pulse, body temperature, etc., so as to judge the current emotional state of the user. However, this method The implementation is complex and not universal. Another common way is to process user-generated data (including microblogs, blogs, etc.) through text analysis to obtain the current emotional state of the user, because the information released by the user is often displayed or implicitly implied. The emotional state of the user is affected, and the popularity of the mobile Internet now makes it more convenient to obtain user data in this...

AI Technical Summary

Problems solved by technology

The traditional single-dimensional recommendation system can no longer meet the personalized needs of users, while the context-sensitive recommendation system can not only better help users solve the problem of information overload, but also fully mine the changes of users' contexts over time and environment. specific needs of

However, in the design of context-based recommendation systems, the strategies for extracting and modeling user context (especially emotional context) and combining with recommendation systems are few and immature, so none of the existing recommendation system algorithms combine emotional context information.

Images