With the popularity of user-generated content video websites,bullet screen comments have become an important means for users to express their emotional opinions.The immediacy and interactivity of bullet screen comments provide rich data re-sources for network sentiment analysis,but their anonymity and short text characteristics bring some difficulties to data analy-sis.This paper proposes a network sentiment analysis system for video bullet screen comments that can effectively identify and filter abnormal users,conduct sentiment analysis,and ultimately achieve topic clustering and visual display of bullet screen comments.The system adopts a front-end and back-end separation architecture,with the front-end based on the Vue framework and the back-end using the Django framework,and data storage is implemented with a MySQL database.Through experimental analysis of bullet screen data from the Bilibili video website,the effectiveness and stability of the system are verified,which promotes the development of network sentiment analysis system.
关键词
弹幕评论/网络舆情分析/情感分析/主题聚类
Key words
barrage comments/online public sentiment analysis/sentiment analysis/topic clustering
维普
万方数据