论文部分内容阅读
文章通过话题聚类及情感强度分析中文微博舆情,实现对微博热点问题的预测,有利于公众舆情引导。首先充分考虑微博短文本的特点,在特征值提取基础上克服了微博短文本易发生“文本漂移”的缺点,并根据微博高频词对微博进行排序实现微博的快速聚类,接着从主观和客观两方面对热点话题的情感强度进行了分析,基于灰色模型跟踪并预测公众情感变化倾向。实验结果表明,本文提出的基于话题聚类及情感强度的中文微博舆情分析方法具有一定的可行性。
Through the topic clustering and emotion intensity analysis of Chinese microblogging public opinion, the article forecasts the hot issues of Weibo and is conducive to public opinion guidance. First of all, taking full account of the characteristics of the short text of microblogging, this paper overcomes the shortcomings of “text drift” and “text drift” of microblog short text based on the feature extraction, and sorts the microblog according to the high frequency words Then, from the subjective and objective aspects, the emotion intensity of the hot topic is analyzed, and the gray model is used to track and predict the change tendency of the public emotion. The experimental results show that the proposed Chinese microblogging public opinion analysis method based on topic clustering and sentiment intensity is feasible.