Google search and social media data can predict outbreaks, University of Waterloo study finds

Data from Google searches and social media posts can serve as an early warning about outbreaks, researchers at the University of Waterloo have found.

Looking at data from January to March 2020, scientists found a correlation between an increase in the number of people looking for symptoms like a cough, runny nose or loss of smell and daily cases of COVID-19.

Because people were likely to search for information about their symptoms before requesting a test, which could take days to return results, Google search data recorded the spike first.

“We could see that you could actually show, I would say nine to ten days before an increase in the number of cases, that something is going to happen,” said the study’s lead investigator, epidemiologist Zahid Butt.

“So in that sense, the signals you get from Google Trends can help you as a kind of early warning system.”

The team also found a similar correlation on Twitter, albeit with a smaller latency, Butt said.

“Twitter is more responsive in the sense that when something happens you see a lot of people posting about that particular disease. So if you look at this study, Google Trends data was better at predicting increases in COVID-19.

Although Butt said digital surveillance like this cannot replace traditional methods of monitoring outbreaks, it could help the health system prepare for an outbreak.

“During the COVID-19 pandemic, what was happening was more reactive. When you had cases, they would try to increase the number of hospital beds or try to add more resources to a place where they were seeing a lot of cases,” Butt said.

“If you’re using this system, you can look at the signals and say ‘Okay, so we’re seeing an increase in people using these kinds of symptom keywords and we can basically notify public health authorities or hospitals. that there is going to be an increase in the number of cases of a particular disease…so be prepared.

The next step for the researchers will be to test whether the model can be used to predict outbreaks of other respiratory diseases with different symptoms.

Butts said they are also investigating whether it could be used to monitor foodborne illnesses or sexually transmitted infections.

Ultimately, the researchers say their findings could be used by public health authorities to develop a real-time surveillance system to flag disease spikes.