Online Postings Could Provide Clues in Food Poisoning Cases
Food poisoning may not seem very mysterious but 80 percent of cases go unsolved each year. With about 48 million cases — including 128,000 hospitalizations and 3,000 deaths — from food poisoning each year, that’s a major problem.
Sometimes the cause is obvious, like the 2019 case in which 209 people came down with E. Coli from a batch of tainted ground beef. But most cases remain mysteries, and a California researcher thinks online consumer comments could provide the solution in at least of those cases.
The problem with cases remaining unsolved is that other consumers can’t be warned about whatever it was that caused the poisoning. That’s where David Goldberg, assistant professor of management information systems at San Diego State University, comes in.
Goldberg proposes a new Food Safety Monitoring System (FSMS) that keeps track of online consumer comments to help track down risky food products. He and his team have published a study in the journal Risk Analysis, setting out the details of what he’s calling the Food Safety Monitoring System (FSMS).
The researchers used an artificial intelligence technology called text mining to analyze comments and reviews from two websites: Amazon.com, the world’s largest e-commerce retailer, and IWasPoisoned.com, a site where consumers alert others to cases of food poisoning.
The database consisted of 11,190 randomly selected Amazon reviews of “grocery and canned food” items purchased between 2000 and 2018, along with 8,596 reviews of food products posted on IWasPoisoned.com. These two datasets allowed the researchers to test the text mining tools before analyzing 4.4 million more Amazon reviews.
Telltale words
The computers were programmed to recognize words associated with foodborne illness such as “sick,” “vomiting,” “diarrhea,” “fever,” and “nausea.” This resulted in a list of flagged products that included specific brands of protein bars, herbal teas, and protein powder. Two of the products flagged by the computers had already been recalled.
An important final step in the monitoring system was a manual review by a panel of 21 food safety experts. Their job was to verify the risk level of a product and suggest a strategy for the manufacturer. For example, in the case of an allergic reaction, experts would recommend investigating alternative ingredients or revising product packaging to include a consumer warning.
In future work, Goldberg hopes to create a way of alerting consumers to food product risks when they are shopping online. Amazon reviewers can give products a star rating and post comments, but it is difficult and time consuming to sort through those reviews looking for health risks.
“If there were a panel that popped up on their screen, it would make them more informed as a consumer and allow them to make a purchasing decision that may ultimately make them feel safer,” says Goldberg.