Skip to content
Stanford University School of Medicine

Mining Twitter to identify cases of foodborne illness

During this year's Big Data in Biomedicine conference at Stanford, Taha Kass-Hout, MD, chief health informatics officer for the U.S. Food and Drug Administration, talked about the potential of social media to monitor food safety saying, "You are what you eat, and in this world, you are what you tweet." Taking this concept into a real-world setting, officials at the Chicago Department of Public Health developed an algorithm to mine Chicago-based tweets for sentiments of food illnesses and, as a result, were able to investigate incidents of food poisoning that would have otherwise gone unnoticed. According to a recent article in Popular Science:

... in a recent project, the city of Chicago sought food poisoning cases by setting an algorithm to mine Chicago-area tweets for complaints. The Chicago Department of Public Health's Twitter bot, plus a new online complaint form, helped the department identify 133 restaurants for inspections over a 10-month period. Twenty-one of those restaurants failed inspection and 33 passed with "critical or serious" violations. Not a bad haul.

Chicago is now working with the health departments of Boston and New York to see if its system could work in those cities, according to a report city researchers published with the U.S. Centers for Disease Control and Prevention. Plus, Twitter isn't the only social media platform cities are looking to mine for public health violations. In May, New York City's department of health reported on using an algorithm to spot Yelp reviews that point to food poisoning cases. New York's Yelp project led the city to discover three restaurants that had multiple violations. All the Yelp cases the city inspected had otherwise gone unreported, New York officials wrote in their own CDC report.

The Chicago bot was pretty simple, as Twitter-reading computer programs go. It searched for tweets geo-located to Chicago and its surrounding suburbs that mentioned "food poisoning." Human staff then read the tweets to determine if they were relevant. (Sounds fun.) Staff marked tweets as relevant or not relevant, to give the algorithm data to better learn what tweets to pull in the future. Then staff members responded to relevant tweets themselves.

Previously: Videos of Big Data in Biomedicine keynotes and panel discussions now available online, Discussing access and transparency of big data in government and Improving methods for tracking flu trends using Twitter

From August 11-25, Scope will be on a limited publishing schedule. During that time, you may also notice a delay in comment moderation. We'll return to our regular schedule on August 25.

Popular posts