Baidu Index and COVID-19 Epidemic Forecast: Evidence From China.

Jianchun Fang,Xinyi Zhang,Hui Liu,Yang Tong,Yuxin Xia,Keke Wu

doi:10.3389/fpubh.2021.685141

Abstract

With the global spread of the Coronavirus epidemic, search engine data can be a practical tool for decision-makers to understand the epidemic's trends. This article uses trend analysis data from the Baidu search engine, the most widely used in China, to analyze the public's attention to the epidemic and the demand for N95 masks and other anti-epidemic materials and information. This kind of analysis has become an important part of information epidemiology. We have analyzed the use of the keywords “Coronavirus epidemic,” “N95 mask,” and “Wuhan epidemic” to judge whether the introduction of real-time search data has improved the efficiency of the Coronavirus epidemic prediction model. In general, the introduction of the Baidu index, whether in-sample or out-of-sample, significantly improves the prediction efficiency of the model.

Highlights

In recent years, with the rapid development of mobile networks, web search data has been widely used in epidemiological research
Yt represents the number of new COVID-19 cases in China every day, Yt−i is a lagging item, and C represents the Baidu index level of keywords such as “Coronavirus epidemic,” “N95 mask,” and “Wuhan epidemic.” σ, βi, and θ are parameters. εi is the error term
As the COVID-19 epidemic continues to spread around the world, the public’s awareness of self-protection continues to increase

Summary

INTRODUCTION

With the rapid development of mobile networks, web search data has been widely used in epidemiological research. Yt represents the number of new COVID-19 cases in China every day, Yt−i is a lagging item, and C represents the Baidu index level of keywords such as “Coronavirus epidemic,” “N95 mask,” and “Wuhan epidemic.” σ , βi, and θ are parameters. The coefficient was negative in November and December 2020 and gradually changed to positive after January 2021 This shows that people’s retrieval of N95 mask keywords changes with the fluctuation of the epidemic, so the overall performance of the parameters is unstable. We use the one-step forward method to compare the prediction performance of the Baidu index expansion model and the benchmark model This benchmark model is defined as a constant forecast, that is, the epidemic trend changes at the same rate as the previous observations.

RESEARCH CONCLUSIONS AND POLICY RECOMMENDATIONS

Findings

DATA AVAILABILITY STATEMENT