Predicting the next infectious disease outbreak may be possible by analyzing trends on Twitter and Google.
Do you want to know when the next vaccine-preventable outbreak will hit? You might want to check social media, according to a new study from investigators at the University of Waterloo in Waterloo, Ontario, Canada, who determined that predicting the next outbreak may be possible by analyzing trends on Twitter and Google.
Whether they love social media or hate it, the truth is that many adults utilize the platform for the latest news. According to a 2016 survey by the Pew Research Center, about 62% of US adults get their news on social media. The nature of social media being what it is, this news is accompanied by commentary from social media users, anxious to share their opinions on the topics at hand. In a perfect world, one would be able to separate the news from opinion; however, these lines have become increasingly blurred to the point that bias has even leaked into “real news outlets” spurning the birth of sensationalism and “fake news.”
One of the top news topics is vaccination. Given the ability to reach millions of individuals in one fell swoop of a tweet, the antivaccine movement is booming on social media. Indeed, the top news article of the year for Contagion® in 2016 was on a study that examined how Facebook users expressed pro-vaccine and anti-vaccine viewpoints. The investigators on that study approached their research aware that although the internet has become a useful tool for information gathering on health issues, it has also become an “echo chamber” where misinformation about vaccines and anti-vaccination attitudes have spread. This has led to a decrease in vaccination rates and in some cases outbreaks of diseases once largely eradicated.
Now, in 2017, the Waterloo investigators are echoing that sentiment with their research and taking it one step further by suggesting that analyzing this information can help to predict outbreaks of vaccine-preventable diseases.
According to a press release on the study, the Waterloo investigators examined both Google searches and geocoded tweets by using artificial intelligence (AI) and a mathematical model. They used the data from the analysis to “analyze public perceptions on the value of getting vaccinated and determine when a population was getting close to a tipping point,” with a tipping point being defined as, “the point at which vaccine coverage declines dramatically due to spreading fear, which could cause large disease outbreaks due to a loss of population immunity.”
The investigators looked at tweets discussing the measles-mumps-rubella vaccine and the user’s sentiment on the vaccines were classified using AI. In addition, they captured Google searches on measles and related subjects. The investigators also created a mathematical model that would predict which sentiments would equate to early warnings signs.
Through this analysis, the researchers found there were “early warning signs of a tipping point 2 years before,” the 2014-2015 Disneyland, California measles outbreak, according to the press release. In addition, “their mathematical model also predicted how the Disneyland outbreak helped push California back from the tipping point by making parents more afraid of the disease than the vaccine.”
Chris Bauch, PhD, a professor of applied mathematics at Waterloo and lead author on the study commented on these findings in the press release stating, “Knowing someone is a smoker cannot tell us for sure whether someone will have a heart attack, but it does tell us that they have an increased risk of heart attack. In the same way, detecting these early warning signals in social media data and Google search data can tell us whether a population is at increased risk of a vaccine scare, potentially years ahead of when it might actually happen. By monitoring people's attitudes towards vaccinations on social media, public health organizations may have the opportunity to direct their resources to areas most likely to experience a population-wide vaccine scare, and prevent it before it starts.”