The researchers combine analyses of social media messages with traditional survey techniques to examine, for example, why people refuse vaccines and how these reasons vary among communities. Their techniques also show promise as tools to gather important information about some common mental illnesses and a variety of public health concerns.

Mark Dredze, an assistant research professor in the Department of Computer Science at The Johns Hopkins University and a member of the Division of Health Sciences Informatics at the school of medicine, developed novel computer algorithms to support the team’s research.

Current survey methods are long, laborious and very expensive, says Dredze, typically resulting in a multiyear process that includes extensive focus groups and large telephone sample sizes. “Our methods allow us to get answers to what people are thinking in real time,” he says. “It’s definitely cheaper and faster, and you can actually respond to an ongoing health crisis. We can do things we never thought we could do before, so it raises the potential for new research.”

For example, the illicit drug market changes rapidly as new illegal drugs become popular. “Traditionally, it takes five years between when an illicit drug is introduced to the market and when we have good data — that’s a big blind spot,” says Dredze. “Using Web data, we’re able to find these drugs and get information much faster. We can say, ‘Here’s a drug to be concerned about. Here’s how people are taking it and what the dosages are.’ If you can get that information into the hands of addiction specialists and emergency department personnel, they can use that information immediately.”

Recently, the team analyzed millions of tweets to gather information on the sentiments toward flu vaccinations. The team identified tweets, geolocated the messages and compared their findings to the Centers for Disease Control and Prevention’s Behavioral Risk Factor Surveillance System. Their results show that states with a higher number of residents who received the flu shot had a higher number of vaccine-positive messages on Twitter.