Authors: Alice Greenway, Future Science Group
In a collaboration between the University of Waterloo (Ontario, Canada), Dartmouth College (NH, USA) and École Polytechnique Fédérale de Lausanne (Lausanne, Switzerland), researchers examined Google searches and geocoded tweets using artificial intelligence. The pooled data was then utilized to examine public perceptions on the value of being vaccinated and determine when a population was close to tipping point.
In the study, published recently in the journal of Proceedings of the National Academy of Sciences, the tipping point of a population was represented by an increase in vaccine refusal and therefore a loss of vaccine coverage and population immunity.
“What this study tells us is that the same mathematical theories used to predict tipping points in phenomena such as changing climate patterns can also be used to help predict tipping points in public health,” explained Chris Bauch, a Professor at the University of Waterloo and the study’s lead author. “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.”
The researchers collected tweets and Google searches that mentioned the keys word ‘measles-mumps-rubella vaccine’ before and after the 2014–2015 Disneyland, California (USA) measles outbreak. Their mathematical model helped predict early warning signs that could be observed in the collected data.
They were able to detect these early warning signals in social media trends and pinpoint that the population reached tipping point 2 years before the outbreak. The mathematical model also demonstrated how the population of California was pushed back from the tipping point after the Disneyland outbreak due to individuals holding more fear for the disease than the vaccine.
“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 increased risk of heart attack,” Bauch commented. “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.
“With the ability to predict the areas where immunity is most at risk due to behavioral factors, we may be able to help eradicate diseases such as measles and polio.”
Sources: Pananosa AD, Burya TM, Wang C et al. Critical dynamics in population vaccinating behavior. Proc. Natl. Acad. Sci. USA. doi:10.1073/pnas.1704093114 (2017) (Epub ahead of print); https://uwaterloo.ca/news/news/social-media-trends-can-predict-tipping-points-vaccine