Deriving anti-epidemic policy from public sentiment: A framework based on text analysis with microblog data

Abstract

Microblog has become the “first scenario” under which the public learn about the epidemic situation and express their opinions. Public sentiment mining based on microblog data can provide a reference for the government’s information disclosure, public sentiment guidance and formulation of epidemic prevention and control policy. In this paper, about 200,000 pieces of text data were collected from Jan. 1 to Feb. 26, 2020 from Sina Weibo, which is the most popular microblog website in China. And a public sentiment analysis framework suitable for Chinese-language scenarios was proposed. In this framework, a sentiment dictionary suitable for Chinese-language scenarios was constructed, and Baidu’s Sentiment Analysis API was used to calculate the public sentiment indexes. Then, an analysis on the correlation between the public sentiment indexes and the COVID-19 case indicators was made. It was discovered that there is a high correlation between public sentiments and incidence trends, in which negative sentiment is of statistical significance for the prediction of epidemic development. To further explore the source of public negative sentiment, the topics of the public negative sentiment on Weibo was analyzed, and 20 topics in five categories were got. It is found that there is a strong linkage between the hot spots of public concern and the epidemic prevention and control policies. If the policies cover the hot spots of public concern in a timely and effective manner, the public negative sentiment will be effectively alleviated. The analytical framework proposed in this paper also applies to the public sentiment analysis and policy making for other major public events.

Social interaction and the successful exit of cultural and creative crowdfunding projects: evidence from the Modian platform

“…The standardized number of comments of project i before crowdfunding stage Source(s): Author's own creation/work project i on day t. Sentiment scores range from 0 to 1, and the closer to 1, the more positive a comment is (Zhao et al, 2022). First, we obtain the sentiment score for each comment added every day.…”

“…In our study, comment sentiment variable is derived through the publication time and text content of a new comment and is recorded as the sentiment score of a comment on project i on day t . Sentiment scores range from 0 to 1, and the closer to 1, the more positive a comment is (Zhao et al. , 2022).…”