A new study shows the potential of an improved system for tracking foodborne illness exploiting online Yelp directory website’s restaurant reviews. The study was published in JAMIA, Journal of the American Medical Informatics Association, by the Columbia University Department of Computer Science.

The new system has been used since 2012 by the New York City (NYC) Department of Health and Mental Hygiene (DOHMH) to identify instances of foodborne illness in NYC restaurants. The system analysed Yelp reviews to identify people experiences that involved foodborne illness. The process is based on the analysis of keywords related to illness, such as “sick” to highlight these relevant reviews. Since the introduction in the DOHMH, 8,523 reviews were recognised as relevant for food poisoning and helped to identify 10 outbreaks of foodborne illness associated with NYC restaurants. In the paper presented, it is explained the evaluation of methods to increase the sensitivity and specificity and improve system performance.

Foodborne illness is a significant issue in the world, a one of the major health problem in the United States. The Centers for Disease Control and Prevention estimates that there are 48 million illnesses and over 3,000 deaths caused by contaminated food in the United States each year. When these occurrences happened in relation to restaurants, they have usually been tracked through the health department complaint registration systems. However, the potential of the nowadays traditionally used social media lies in the fact that offer an alternative way to express feelings and describe experiences. In fact, the new platforms are used to disclose incidents that may not have been reported in the traditional ways, such as through established complaint systems.

For instance, youths are less likely to report foodborne illness via traditional channels. However, on the other hand, the use of online reviews is increasingly becoming more popular and same goes for the incorporation of the analysis of such online reviews in the public health surveillance systems. Search engines and social media data has been exploited to monitor and identify outbreaks of different infectious diseases, such as influenza. A comparison between the use of social media and internet data, and traditional methods of detecting outbreaks of infectious diseases shown that the online methods were the first to report outbreaks in 70% of cases.

Not surprisingly, the initial pilot study of the DOHMH system, from July 1 2012 to March 31 2013, found that only 3% of illness incidents discovered via online reviews had been reported via NYC’s established complaint system. Due to the success of the pilot study, DOHMH has integrated Yelp reviews into its foodborne illness complaint surveillance system and continues to mine Yelp reviews and investigate those pertaining to foodborne illness. DOHMH looks forward to implementing the improved system and continues to work with Columbia University to integrate new data sources, including Twitter, into the foodborne illness complaint system.

“We find that the application of machine learning, specifically in the form of document classification techniques, can contribute greatly to public health surveillance in social media, explained lead researcher Thomas Effland. “Our future work will improve upon these techniques and target their application to foodborne illness surveillance in other forms of social media, such as Twitter, as well as other key indicators in public health.”

Written by: Pietro Paolo Frigenti

Journal Reference: Effland, T., Lawson, A., Balter, S., Devinney, K., Reddy, V., Waechter, H., Gravano, L., & Hsu, D. (2018). Discovering foodborne illness in online restaurant reviews. Journal of the American Medical Informatics Association.