Using Social Media to Predict Food Deserts in the United States: Infodemiology Study of Tweets

Abstract

BackgroundThe issue of food insecurity is becoming increasingly important to public health practitioners because of the adverse health outcomes and underlying racial disparities associated with insufficient access to healthy foods. Prior research has used data sources such as surveys, geographic information systems, and food store assessments to identify regions classified as food deserts but perhaps the individuals in these regions unknowingly provide their own accounts of food consumption and food insecurity through social media. Social media data have proved useful in answering questions related to public health; therefore, these data are a rich source for identifying food deserts in the United States.ObjectiveThe aim of this study was to develop, from geotagged Twitter data, a predictive model for the identification of food deserts in the United States using the linguistic constructs found in food-related tweets.MethodsTwitter’s streaming application programming interface was used to collect a random 1% sample of public geolocated tweets across 25 major cities from March 2020 to December 2020. A total of 60,174 geolocated food-related tweets were collected across the 25 cities. Each geolocated tweet was mapped to its respective census tract using point-to-polygon mapping, which allowed us to develop census tract–level features derived from the linguistic constructs found in food-related tweets, such as tweet sentiment and average nutritional value of foods mentioned in the tweets. These features were then used to examine the associations between food desert status and the food ingestion language and sentiment of tweets in a census tract and to determine whether food-related tweets can be used to infer census tract–level food desert status.ResultsWe found associations between a census tract being classified as a food desert and an increase in the number of tweets in a census tract that mentioned unhealthy foods (P=.03), including foods high in cholesterol (P=.02) or low in key nutrients such as potassium (P=.01). We also found an association between a census tract being classified as a food desert and an increase in the proportion of tweets that mentioned healthy foods (P=.03) and fast-food restaurants (P=.01) with positive sentiment. In addition, we found that including food ingestion language derived from tweets in classification models that predict food desert status improves model performance compared with baseline models that only include socioeconomic characteristics.ConclusionsSocial media data have been increasingly used to answer questions related to health and well-being. Using Twitter data, we found that food-related tweets can be used to develop models for predicting census tract food desert status with high accuracy and improve over baseline models. Food ingestion language found in tweets, such as census tract–level measures of food sentiment and healthiness, are associated with census tract–level food desert status.

Using COVID-19 Vaccine Attitudes Found in Tweets to Predict Vaccine Perceptions in Traditional Surveys: Infodemiology Study

“…In this study, we found that COVID-19 vaccine attitudes in the HPS, measured as vaccine compliance and hesitancy, can be predicted using social media attitudes toward vaccines, measured via sentiments and emotions toward vaccines. The results of this study support the efforts of researchers, who over the past few years have looked at social media as a data source, citing the availability of readily available data and no-or low-cost data collection efforts [40,41].…”

Exploring food poverty experiences in the German Twitter-Sphere

“…Some tweets also addressed concerns related to altered or extreme climatic conditions, particularly the potential health impacts of extreme heat. Given innovative studies that utilize Twitter data to identify geographical dynamics or food deserts associated with inadequate access to healthy food [54,55] and the growing need for research to focus on charity food supply options in rural areas these aspects merit further investigation. Additionally, the risks posed by the climate crisis, particularly for socioeconomically disadvantaged groups, should be integrated more extensively into public health research.…”

“…The work on both terms is taken into account here, but in the further course of the data analysis reference is made exclusively to the theoretical assumptions on food poverty [10,19]. Some social media-related studies on food insecurity or poverty have analysed food-related tweets and metadata to identify geographical dynamics or food deserts associated with inadequate access to healthy foods [54,55]. Other studies have focused on sentiment analysis to examine emotions or reactions expressed on Twitter, particularly in response to emergency food supplies [56].…”

Using Natural Language Processing to Explore Social Media Opinions on Food Security: Sentiment Analysis and Topic Modeling Study

“…Previous studies have used a variety of NLP techniques as part of an infodemiological process to explore different areas of food security for different purposes; however, they have not combined sentiment and topic analysis across time and in relation to social media engagement, as in this study. Studies have used NLP to predict food deserts using the sentiment and nutritional value of the foods mentioned on social media within different geographic regions [73] and to summarize the academic literature on community gardens [74]. Research similar to this study includes a study by Mayasari et al [75] that used Google Trends to explore food security and dietary and lifestyle behaviors during the COVID-19 pandemic.…”