Chick-fil-A Uses AI to ID Signs of Foodborne Illness

Social media posts plus algorithms are 78% accurate, company reports.

May 30, 2019

ATLANTA—Chick-fil-A is using algorithms to analyze social media for potential food safety issues throughout its 2,400-plus restaurants, according to Venturebeat.com.

During a recent presentation in Boston, Davis Addy, senior principal IT leader of food safety and product quality, shared information on the AI that Chick-fil-A uses to track problematic health trends around its restaurants.

“For us in this journey with analytics and food safety, we’re going from a place of hindsight to insight … and eventually foresight so we can be more proactive in helping our restaurants better identify and address food safety risks,” said Addy.

Social media is the most common customer feedback channel for food safety-related incidents, Addy noted, but it also provides challenges. Posts are inconsistent grammatically and tonally. Some users are more facetious and controversial than others, and isolated posts can be difficult to correlate with real-world events.

Chick-fil-A’s goal was to develop an AI framework that could reliably identify keywords, phrases and customer sentiment from social media posts to spot emerging foodborne illness. Its AWS-hosted solution processes restaurant review data every 10 minutes from a range of social platforms. The posts are filtered for more than 500 keywords (including words like “illness,” “food poisoning,” “vomit,” “throw up,” “barf” and “nausea”), and AWS Comprehend, Amazon’s natural language processing service, checks sentiment and determines legitimacy.

Addy said that AWS Comprehend had trouble determining the sentiment of certain food-related phrases, but after collaborating with Amazon, the Chick-fil-A team has been able to achieve up to 78% accuracy.

If an issue is discovered, store managers receive notifications via a mobile app, which highlights words the algorithm identified and enables them to drill in to see full posts. From there, they’re able to contact customers directly (through the social platform), if they choose. The data also go to a corporate dashboard, where they are plotted over time to make trends easier to spot.

Food safety isn’t the only domain Chick-fil-A thinks might benefit from technology. The chain is experimenting with computer vision systems that warn employees who’ve been handling raw chicken to wash their hands before moving to other areas of the kitchen. A separate AI-driven system instructs team members how to rinse their hands thoroughly. If employees washed their hands “as often as they should,” Addy said, they’d reduce the risk of foodborne illness by as much as 80%.

Advertisement
Advertisement
Advertisement