Food is an integral part of everyday life, and food choices directly affect one’s health. Both academics and practitioners have attempted to help consumers make good decisions about their food choices and recommended better or healthier alternatives. However, in thinking about food it is important to put it in context, as each food item is often combined with other food items to create the gestalt of a recipe or meal. Understanding the complex interaction between food items that are used or consumed together is crucial to provide effective recommendations. In this research, I leverage tools from machine learning and textual analysis like the embedding approach for representation learning to understand food in its context and to build recommender systems that account for the complementarity or fit of co-consumed food items. I show that this consideration of fit among food items can lead to better and healthier food recommendations.

The disproportionate concentration of unhealthy food in communities of color in the United States may contribute to health inequities and food insecurity. Gentrification has been associated with residents’ increased adverse health outcomes in its early and rapid phases. This study adds to the growing body of research by examining the relationship between gentrification, the food environment, food habits (the interplay between food chances and food choices), and health in New York City. I used a mixed methods approach to assess the food landscape in NYC between 1990 and 2014, using group-based trajectory modeling, the National Establishments Time-Series database, census data, and in-depth interviews with mothers from the Columbia Center for Children’s Environmental Health study. I found that the growth in the food environment was unevenly distributed. While healthy food chances declined across all examined neighborhoods, unhealthy food chances quickly grew, commanding dominance. It was gentrifying neighborhoods; however, that surprisingly experienced the most remarkable growth in unhealthy food chances compared to other neighborhoods. A cross-tabulation of the food chance trajectories of New York City census tracts indicated the presence of food ecologies that exhibit both healthy and unhealthy food chances. There was a strong association between the type of food ecology and gentrification status (p < 0.001). The in-depth interviews corroborated these findings and revealed that food insecurity is a by-product of gentrification in two ways. First, neighborhoods in the early stages of gentrification are inundated with unhealthy food chances, such as fast-food chains, without adequate access to quality, fresh, healthy foods. Secondly, when healthy food chances finally arrive in resource-deprived areas through gentrification, families are forced to relocate to areas without access to fresh, affordable, healthy foods due to the increased cost of living. This cycle of food insecurity is inequitable due to historical racial segregation, exploitative capitalistic markets, and racist stereotypes. Speculators invest in unhealthy food chances aligned with pre-existing stereotypes, assumptions, and beliefs that such communities do not or will not consume healthier foods. Therefore, a cycle of structural racism reinvents itself through this investment in unhealthy food chances, constructing food deserts and swamps bestowed upon communities experiencing poverty and disproportionate adverse cardiovascular health conditions. Strengthening policy focused on the relationship between gentrification mitigation and health outcomes is needed.

The purpose of this project was to explore parent perceptions about their children's weight and the perceived barriers to implementing healthy eating habits and patterns of physical activity for their children.

The purpose of this project was to explore parent perceptions about their children's weight and the perceived barriers to implementing healthy eating habits and patterns of physical activity for their children.