Disease outbreaks trackable with Twitter

January 22, 2013
Credit: Brigham Young University

(Medical Xpress)—This flu season you've probably seen a number of friends on social media talking about symptoms.

New research from Brigham Young University says such posts on could actually be helpful to looking for a head start on outbreaks.

The study sampled 24 million tweets from 10 million unique users. They determined that accurate location information is available for about 15 percent of tweets (gathered from user profiles and tweets that contain ). That's likely a for an early-warning system that could monitor terms like "fever," "flu" and "coughing" in a city or state.

"One of the things this paper shows is that the distribution of tweets is about the same as the distribution of the population so we get a good representation of the country," said BYU professor Christophe Giraud-Carrier. "That's another nice validity point especially if you're going to look at things like diseases spreading."

Professor Giraud-Carrier (@ChristopheGC) and his computer science students at BYU report their findings in a recent issue of the Journal of Medical Internet Research.

The researchers found surprisingly less data than they expected from Twitter's feature that enables tweets to be tagged with a location. They found that just 2 percent of tweets contained the GPS info. That's a much lower rate than what Twitter users report in surveys.

"There is this disconnect that's well known between what you think you are doing and what you are actually doing," Giraud-Carrier said.

Location info can more often be found and parsed from user profiles. Of course some people use that location field for a joke, i.e. "Somewhere in my imagination" or "a cube world in Minecraft." However, the researchers confirmed that this user-supplied data was accurate 88 percent of the time. Besides the jokes, a portion of the inaccuracies arise from people tweeting while they travel.

The net result is that public health officials could capture state-level info or better for 15 percent of . That bodes well for the viability of a Twitter-based disease monitoring system to augment the confirmed data from sentinel clinics.

"The first step is to look for posts about symptoms tied to actual location indicators and start to plot points on a map," said Scott Burton, a graduate student and lead author of the study. "You could also look to see if people are talking about actual diagnoses versus self-reported symptoms, such as 'The doctor says I have the flu.'"

The computer scientists collaborated with two BYU health science professors on the project. Professor Josh West says speed is the main advantage Twitter gives to health officials.

"If people from a particular area are reporting similar symptoms on Twitter, could put out a warning to providers to gear up for something," West said. "Under conditions like that, it could be very useful."

BYU undergraduate Kesler Tanner is a co-author on the study. He wrote the code to obtain the data from Twitter. When he graduates in April, he'll be headed off to graduate school to earn a Ph.D.

Earlier this year, this same group of researchers published a study showing that most exercise apps are based on bad info.

Explore further: Twitter marks fifth anniversary of public launch

More information: www.jmir.org/2012/6/e156/

Related Stories

Twitter marks fifth anniversary of public launch

July 15, 2011
Twitter marked the fifth anniversary of its public launch Friday with a slew of statistics demonstrating the explosive growth of the real-time blogging service.

Twitter says its ads pay off for candidates

October 10, 2012
Twitter released a study Wednesday showing its paid messages pay off for political candidates, not only in garnering attention but in driving campaign contributions.

Twitter clocks half-billion users: monitor

July 30, 2012
Over 500 million people are on micro-blogging site Twitter and Americans and Brazilians are the most connected, according to a study by social media monitor Semiocast released Monday.

Recommended for you

Google searches can be used to track dengue in underdeveloped countries

July 20, 2017
An analytical tool that combines Google search data with government-provided clinical data can quickly and accurately track dengue fever in less-developed countries, according to new research published in PLOS Computational ...

MRSA emerged years before methicillin was even discovered

July 19, 2017
Methicillin resistant Staphylococcus aureus (MRSA) emerged long before the introduction of the antibiotic methicillin into clinical practice, according to a study published in the open access journal Genome Biology. It was ...

New test distinguishes Zika from similar viral infections

July 18, 2017
A new test is the best-to-date in differentiating Zika virus infections from infections caused by similar viruses. The antibody-based assay, developed by researchers at UC Berkeley and Humabs BioMed, a private biotechnology ...

'Superbugs' study reveals complex picture of E. coli bloodstream infections

July 18, 2017
The first large-scale genetic study of Escherichia coli (E. coli) cultured from patients with bloodstream infections in England showed that drug resistant 'superbugs' are not always out-competing other strains. Research by ...

Ebola virus can persist in monkeys that survived disease, even after symptoms disappear

July 17, 2017
Ebola virus infection can be detected in rhesus monkeys that survive the disease and no longer show symptoms, according to research published by Army scientists in today's online edition of the journal Nature Microbiology. ...

Mountain gorillas have herpes virus similar to that found in humans

July 13, 2017
Scientists from the University of California, Davis, have detected a herpes virus in wild mountain gorillas that is very similar to the Epstein-Barr virus in humans, according to a study published today in the journal Scientific ...

0 comments

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.