Sentiment analysis for news and social media in COVID-19
Xinran Yu, Chao Zhong, Dandan Li, Wei Xiang Xu · 2020
During the COVID-19 epidemic, the news is overwhelming in people's daily life. So, we aim to extract key information from a large amount of public news. This paper focus on the daily sentiment distribution of news and public opinion on Weibo that refers to the key word COVID-19. First, we refining the key news from all the news in a day to deal with long and large news data. Second, we transformer the headline into a high-dimensional vector. And then, divided them into k categories on the strength of k-means clustering algorithm. Finally, choose the closet news to the mean vector as the key news of the day. Moreover, we conduct sentiment analysis on all key news and Weibo data. By comparing the sentiment trend of news and Weibo, this study provides a new channel to analyze social public opinion.