Tracking COVID-19 using online search

Abstract

Previous research has demonstrated that various properties of infectious diseases can be inferred from online search behaviour. In this work we use time series of online search query frequencies to gain insights about the prevalence of COVID-19 in multiple countries. We first develop unsupervised modelling techniques based on associated symptom categories identified by the United Kingdom’s National Health Service and Public Health England. We then attempt to minimise an expected bias in these signals caused by public interest—as opposed to infections—using the proportion of news media coverage devoted to COVID-19 as a proxy indicator. Our analysis indicates that models based on online searches precede the reported confirmed cases and deaths by 16.7 (10.2–23.2) and 22.1 (17.4–26.9) days, respectively. We also investigate transfer learning techniques for mapping supervised models from countries where the spread of the disease has progressed extensively to countries that are in earlier phases of their respective epidemic curves. Furthermore, we compare time series of online search activity against confirmed COVID-19 cases or deaths jointly across multiple countries, uncovering interesting querying patterns, including the finding that rarer symptoms are better predictors than common ones. Finally, we show that web searches improve the short-term forecasting accuracy of autoregressive models for COVID-19 deaths. Our work provides evidence that online search data can be used to develop complementary public health surveillance methods to help inform the COVID-19 response in conjunction with more established approaches.

The Presumed Influence of COVID-19 Misinformation on Social Media: Survey Research from Two Countries in the Global Health Crisis

“…Previous IPI literature scarcely focuses on public health issues and is limited in one single study context [ 11 , 46 ]. When the misinformation of COVID-19 disease is intensifying on social media from all over the world [ 8 ], it is urgent to understand the public perception of misinformation proliferation toward this global pandemic and its behavioral outcomes in societies. By linking negative emotions, PIMO, and public support for restrictive and connective actions in one theoretical framework, we studied both antecedents and outcomes of perceived media influence on others in crisis situations.…”

“…However, without prudent journalistic judgments of media content online, misinformation, referring to false and misleading information, began circulating rapidly on social media [ 6 , 7 ]. For instance, misinformation has made many people believe that using salt water or drinking bleach could kill the virus during the pandemic [ 8 ]. The general public, especially those who cannot easily identify misinformation and differentiate the misleading messages from health facts [ 9 ], might conduct misinformed behaviors, such as panic purchasing actions and mass meetings without proper protection.…”

Psychological Health Status Evaluation of the Public in Different Areas Under the Outbreak of Novel Coronavirus Pneumonia

“…Many research communities, funding agencies, and third parties are taking actions to support the fight against the pandemic with their own expertise and resources: a few Covid-19 papers highly cited, with substantial news and social media attention have been found [16]. The time series of online search queries in relation to confirmed Covid-19 cases data across multiple countries are analyzed [17]. Natural language processing methods are developed to analyze a large collection of Covid-19 literature containing study reports from hospitals all over the world, reconcile these results, and draw unbiased and universally-sensible conclusions about the correlation between radiological findings and Covid-19 [18].…”

Internet Search Effort on Covid-19 and the Underlying Public Interventions and Epidemiological Status

“…This resulted in the proportion (%) of Covid-19 news media articles per day. This was done in order to examine the correlation between web search effort and news cover on the topic and quantify the extend that web search is related with news (Bento et al 2020, Lampos et al 2021).…”