An “Infodemic”: Leveraging High-Volume Twitter Data to Understand Public Sentiment for the COVID-19 Outbreak

This article has 1 evaluations Published on
Read the full article Related papers
This article on Sciety

Abstract

Background

Twitter has been used to track trends and disseminate health information during viral epidemics. On January 21, 2020, the CDC activated its Emergency Operations Center and the WHO released its first situation report about Coronavirus disease 2019 (COVID-19), sparking significant media attention. How Twitter content and sentiment has evolved in the early stages of any outbreak, including the COVID-19 epidemic, has not been described.

Objective

To quantify and understand early changes in Twitter activity, content, and sentiment about the COVID-19 epidemic.

Design

Observational study.

Setting

Twitter platform.

Participants

All Twitter users who created or sent a message from January 14th to 28th, 2020.

Measurements

We extracted tweets matching hashtags related to COVID-19 and measured frequency of keywords related to infection prevention practices, vaccination, and racial prejudice. We performed a sentiment analysis to identify emotional valence and predominant emotions. We conducted topic modeling to identify and explore discussion topics over time.

Results

We evaluated 126,049 tweets from 53,196 unique users. The hourly number of COVID-19-related tweets starkly increased from January 21, 2020 onward. Nearly half (49.5%) of all tweets expressed fear and nearly 30% expressed surprise. The frequency of racially charged tweets closely paralleled the number of newly diagnosed cases of COVID-19. The economic and political impact of the COVID-19 was the most commonly discussed topic, while public health risk and prevention were among the least discussed.

Conclusion

Tweets with negative sentiment and emotion parallel the incidence of cases for the COVID-19 outbreak. Twitter is a rich medium that can be leveraged to understand public sentiment in real-time and target public health messages based on user interest and emotion.

Funding

None.

Related articles

Related articles are currently not available for this article.