AUTHOR=Chen Jingguo , Mi Hao , Fu Jinyu , Zheng Haitian , Zhao Hongyue , Yuan Rui , Guo Hanwei , Zhu Kang , Zhang Ya , Lyu Hui , Zhang Yitong , She Ningning , Ren Xiaoyong 

TITLE=Construction and validation of a COVID-19 pandemic trend forecast model based on Google Trends data for smell and taste loss

JOURNAL=Frontiers in Public Health

VOLUME=Volume 10 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/public-health/articles/10.3389/fpubh.2022.1025658

DOI=10.3389/fpubh.2022.1025658

ISSN=2296-2565

ABSTRACT=Aims To build a forecast model for the trend of the COVID-19（Corona Virus Disease 2019） prediction based on the Google Trends of smell and taste loss, and explore the role of smell and taste changes in preventing and controlling the COVID-19 epidemic. Results From January 6th, 2020, to November 28th, 2021, a total of 99 weeks of data were analyzed. When the delay period was set from 1 to 3 weeks, the interpretation sequence (Google Trends of loss of smell and taste data) and response sequence (number of new confirmed cases of COVID-19 per week) were significantly correlated (P < 0.01). The ARIMAX forecast model showed that: around the globe and in India, the absolute error distribution of the model predicting the number of newly diagnosed COVID-19 in the next three weeks was between 0.08 and 3.10 (the maximum value is 100, the same below); in the United States, the absolute error of forecast in the next three weeks was distributed between 9.19 and 16.99, and the forecast effect was relatively accurate. The results showed that when the end position of the response sequence was the midpoint of the ascending segment, the absolute error of the model forecast value in the next four weeks was distributed between 0.15 and 5.77. When the last sites of the response sequence were the extreme points (May 2nd, 2021, August 29th, 2021, June 20th, 2021, and October 17th, 2021), the model could accurately forecast the trend of the number of confirmed cases after the extreme point. The model could successfully predict the development trend of COVID-19. Google Trends for loss of smell and taste could accurately forecast the development trend of COVID-19 in advance of 1~3 weeks.