Back

Predicting social distancing index during COVID-19 outbreak through online search engines trends

Lins Filho, P. C.; Freitas, J. L. d. M.; Araujo, M. M. S. d.; Macedo, T. S. d.; Ferreira, A. K. A.; Melo, M. C. F. d.; Silva, E. L. M. S. d.; Caldas, A. d. F.

2020-05-30 health informatics
10.1101/2020.05.28.20115816 medRxiv
Show abstract

Online-available information has been considered an accessory tool to estimate epidemiology and collect data on diseases and population behavior patterns. This study aimed to explore the potential use of Google and YouTube relative search volume to predict social distancing index in Brazil during COVID-19 outbreak and verify the correlation between social distancing measures with the course of the epidemic. Data concerning the social distancing index, epidemiological data on COVID-19 in Brazil and the search engines trends for "Coronavirus" were retrieved from online databases. Multiple linear regression was performed and resulted in a statistically significant model evidencing that Google and YouTube relative search volumes are predictors of the social distancing index. The Spearman correlation test revealed a weak correlation between social distancing measures and the course of the COVID-19 epidemic. Health authorities can apply these data to define the proper timing and location for practicing appropriate risk communication strategies.

Matching journals

The top 4 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.