Tracking tweets helped Las Vegas prevent food poisoning
- By Derek Major
- Mar 16, 2016
Foodborne illnesses affect more than 48 million people in the United States annually, and many of those sickened by food at restaurants take to Twitter to complain.
While details of food poisoning sounds like oversharing to some, researchers from the University of Rochester used those tweets to develop nEmesis. Designed for health departments, the app leverages social media, natural language processing and artificial intelligence to identify tweets related to food poisoning, connect them to restaurants and identify where outbreaks are originating.
In an experiment that spanned three months, officials from the Las Vegas Health Department used the app to augment its system of randomly selecting restaurants to inspect. nEmesis scanned an average of 16,000 tweets per day from 3,600 different Twitter accounts to suggest restaurants Twitter users associated with foodborne illnesses.
In the test, half of the health department restaurant inspection selections were made randomly, and half were selected with the help of nEmesis. Inspectors did not know of the change in the system.
The results of the experiment showed the tweet-based system resulted in citations in 15 percent of inspections compared with 9 percent using the random system. The team estimated that using nEmesis prevented 9,000 food poisoning cases and 557 hospitalizations in Las Vegas during the three-month experiment.
"Adaptive inspections are significantly more effective and can make a real dent in the statistics," Adam Sadilek, a researcher who worked on the project, said. "This case shows how you can use public data to improve public health."
City officials agreed. “nEmesis has proved to be a useful tool for quickly and accurately identifying facilities in need of support, education or regulation by the health department,” Lauren DiPrete, a senior environmental health specialist for the Southern Nevada Health District, said.
Although the program was used for restaurants, Brian Labus, a visiting research assistant professor at the University of Nevada Las Vegas’ School of Community Health Sciences, said he believes nEmesis can be used to track other public health complaints.
“This happens to be restaurants, but the method can also be used for bedbugs,” Labus said. “Similarly, you can look what people tweet about after they visit their doctor or hospital. We're just beginning to scratch the surface of what's possible.”
Derek Major is a former reporter for GCN.