Using Yelp Reviews to Identify Foodborne Illness Outbreaks in NYC

Epidemiologists at the New York City Health Department and Columbia University have developed a computer system that detects food-borne illness and outbreaks in NYC area restaurants based on keywords in Yelp reviews, 311 and reports from healthcare providers. The Health Department has identified and investigated approximately 28,000 complaints of suspected food-borne illness overall since 2012.

Speaking of the partnership between the Health Department and Columbia University, the NYC Health Commissioner, Dr. Mary Bassett said, “Today we not only look at complaints from 311, but we also monitor online sites and social media. I look forward to working with Columbia University on future efforts to build on this system. The Health Department follows up on all reports of food-borne illness – whether it is reported to 311 or Yelp.”  

Every year, thousands of NYC residents risk sickness from harmful bacteria, viruses and parasites by consuming contaminated food and drink. The most common sources of reported food poisoning are from raw or under-cooked poultry, meat, eggs, fish, shellfish and unpasteurized milk. Fruits and vegetables also can be contaminated if they are handled or processed in unclean facilities or if they come in contact with contaminated fertilizer or water. Contamination may also occur if food touches other contaminated food or is incorrectly handled by a sick food worker.

Identifying reports of food poisoning using social media is reflective of the times and utilizes valuable crowd-sourced technology-based information that NYC residents are readily sharing. Brooklyn Borough President Eric Adams applauded Commissioner Bassett for “embracing the role that crowd-sourcing technology can play in identifying outbreaks of food-borne illness. Public health must be forward-thinking in its approach to triaging both everyday and acute medical concerns.”


To access the article, titled: ‘Discovering foodborne illness in online restaurant reviews,’ click here.



Skip to toolbar