Study uses real-time Twitter data to understand vaccine refusal

A multi-institutional team of researchers has initiated a study which will draw in part on Twitter analyses to better understand vaccine refusal, George Washington University announced in a press release.

“People really do tweet about everything, and conversations about vaccines are no exception,” David Broniatowski, PhD, assistant professor in the School of Engineering and Applied Science at the George Washington University, in a press release. “Parents and patients freely share their fears and concerns about vaccines. While it typically takes years to collect meaningful information about why people refuse vaccines, using surveys and searching Twitter brings immediate results.”

Targeted Twitter searches

The study will involve a combination of Twitter searches and conventional survey approaches to evaluate the reasons for vaccine refusal, and analyze variations in refusal patterns between different demographics and communities. The study is particularly topical in light of the severity of the current flu seasons, as well as recent outbreaks of vaccine-preventable illnesses such as measles, which has re-emerged in 17 states and the District of Columbia. Mumps has also been reported among players in the National Hockey League.

According to researcher Karen Hilyard, PhD, assistant professor at the College of Public Health at the University of Georgia, the study’s combination of traditional surveys and Twitter data is likely to offer a diverse representation of different demographics.

“Survey data tend to draw from older, white, rural households, whereas younger, urban minorities are overrepresented on Twitter," Hilyard said in the press release. "These two techniques complement each other perfectly.”

The researchers will conduct targeted Twitter searches for attitudes about vaccine refusal or hesitancy using new computer algorithms being developed by researcher Mark Dredze, PhD, assistant research professor at Johns Hopkins University.

“We hope to gain insights into people’s reasoning about vaccines by automatically processing millions of Twitter messages,” Dredze said in the release.

The study is funded by a 5-year, $1.6 million grant from the National Institute of General Medical Sciences of the National Institutes of Health. Since receiving the grant last month, Broniatowski, Hilyard and Dredze have begun assessing millions of tweets to collect data on attitudes about flu vaccination. After identifying tweets pertaining to vaccination, they geo-located the messages and analyzed their findings in relation to data from the CDC’s Behavior Risk Factor Surveillance System. They found that states with more residents who underwent flu vaccination also had a higher number of tweets reflecting vaccine-positive attitudes.

Twitter makes surveys easier

“This was really surprising and exciting,” Hilyard said in the press release. “It shows that we can get this type of information from Twitter faster, cheaper and more easily. Frankly, it's a game changer when it comes to health surveys, especially as we dig deeper to examine more complex attitudes and beliefs among different demographic groups.”

Extracting real-time data on vaccine attitudes from social media will be useful in helping health officials to respond more quickly to the next outbreak, and will expedite necessary research into vaccine refusal and hesitancy.

“The dream would be to get ahead of the next outbreak,” Broniatowski said in the press release. “How can we take what we learn here and better educate parents about the merits of vaccines and other public health decisions that seem risky? If we could do that, then hopefully we'd be able to prevent the next measles outbreak.”

Other researchers in the study include Eili Klein, PhD, assistant professor at the Johns Hopkins School of Medicine; Joshua Epstein, PhD, professor of emergency medicine at Johns Hopkins, and Sandra Quinn, PhD, professor of family science at the University of Maryland.