短视频传播受众情绪预判研究  

Research on predicting the audience emotions in short video dissemination

作　　者：李奕霏 陈珊 LI Yifei;CHEN Shan(School of Media,Linyi University,Linyi 276000,Shandong,China)

机构地区：[1]临沂大学传媒学院,山东临沂276000

出　　处：《智能计算机与应用》2024年第10期87-91,共5页Intelligent Computer and Applications

基　　金：2023年度山东省社会科学规划研究项目(22CLYJ04)。

摘　　要：在短视频传播中,用户情感分析是探索视频媒体传播规律的基础。短视频弹幕包含了分析用户情感倾向的重要信息。因此,通过短视频弹幕识别受众的情感倾向对视频媒体传播具有重要意义。本文利用视频媒体中弹幕信息来分析传播受众的情绪态势,以计算机深度学习模型为核心设计一个新型的面向短视频弹幕情绪识别的预测模型,通过将短视频传播受众的情绪分成5类,构建用户情绪空间,并借助浅度学习模型来实时预判受众群体的情绪倾向。In short-video dissemination,user emotion analysis is the foundation for exploring the dissemination laws of video media.Short-video bullet comments contain important information for analyzing the emotional tendencies of users.Therefore,identifying the emotional tendencies of the audience through short-video bullet comments is of great significance for video media dissemination.This paper uses the bullet comment information in video media to analyze the emotional situation of the dissemination audience.And the paper designs a new prediction model for short-video bullet comment emotion recognition centered around a computer deep learning model.By dividing the emotions of the short-video dissemination audience into five categories,a user emotion space is constructed,and a shallow learning model is used to predict the emotional tendencies of the audience group in real time.

关 键 词：短视频 弹幕 情绪预判 预测模型 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]