Words Speak Louder Than Numbers: Estimating China’s COVID-19 Severity with Deep Learning

31 Pages Posted: 29 Dec 2020

See all articles by Julian TszKin Chan

Julian TszKin Chan

Bates White Economic Consulting

Kwan-Yuet Ho

Data Scientist

Kit Lee

Data Scientist

Weifeng Zhong

Mercatus Center at George Mason University

Kawai Leung

Independent Researcher

Date Written: December 2020

Abstract

We develop a deep learning algorithm to estimate the severity of the 2020 COVID-19 outbreak in China by analyzing the language of the People’s Daily, China’s official newspaper. The algorithm uses the 2002–2003 SARS outbreak as the benchmark and learns how the newspaper’s language evolved during the epidemic cycle. It then maps the daily coverage of the coronavirus outbreak to the SARS timeline and, hence, estimates its relative position in the benchmark epidemic cycle. We call this timeline-based measure the Policy Change Index for Outbreak. We find a pronounced discrepancy between our severity measure and China’s official numbers of diagnosed cases. We also demonstrate that our indicator is more informative about the outbreak’s severity than a conventional sentiment analysis.

Keywords: policy change, propaganda, deep learning, coronavirus, COVID-19, SARS, outbreak

JEL Classification: C63, D83, I18, P49

Suggested Citation

Chan, Julian TszKin and Ho, Kwan-Yuet and Lee, Kit and Zhong, Weifeng and Leung, Kawai, Words Speak Louder Than Numbers: Estimating China’s COVID-19 Severity with Deep Learning (December 2020). Mercatus COVID-19 Response Working Paper Series, Available at SSRN: https://ssrn.com/abstract=3754453 or http://dx.doi.org/10.2139/ssrn.3754453

Julian TszKin Chan (Contact Author)

Bates White Economic Consulting ( email )

1300 Eye Street NW
Suite 600
Washington, DC 20005
United States

Kwan-Yuet Ho

Data Scientist ( email )

Kit Lee

Data Scientist

Weifeng Zhong

Mercatus Center at George Mason University ( email )

3434 Washington Blvd., 4th Floor
Arlington, VA 22201
United States

HOME PAGE: http://www.weifengzhong.com/

Kawai Leung

Independent Researcher

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
29
Abstract Views
849
PlumX Metrics