Logistic Regression Classifier-Based Indications of Foodborne Illness from Yelp Reviews: Exploring Temporal Variation and Socioeconomic Context (2012 - 2021)

Foodborne illnesses are gastrointestinal conditions traced to consuming food contaminated by hazardous bacteria, toxins, parasites, viruses, or chemicals. Restaurants are critical venues at which to investigate foodborne illness outbreaks given shared sourcing, preparation, and distribution of foods. There is insufficient public use of formal channels to report illness after food consumption. Online social media platforms are abundant sources of user-generated content that provide critical insights into the needs of individuals and populations. The Adaptive Information Extraction from Social Media for Actionable Inferences in Public Health project is a collaboration between the Columbia University Department of Computer Science and the New York City Department of Health and Mental Hygiene in which we extract Yelp data and process them via machine learning classifiers to identify potential outbreaks of foodborne illness in connection with consuming food from restaurants.

This poster, presented at the Columbia University Pathways Program (CUPP) Symposium on July 25, 2023, presents an analysis of bias adjusted logistic regression classifier output and median household income by U.S. Census tract between 2012 - 2021 to provide insight into the spatial distribution of user-generated indications of potential foodborne illness events and association with income disparities.