The COVID-19 pandemic initially caused worldwide concerns about food insecurity. Tweets analyzed in real-time may help food assistance providers target food supplies to where they are most urgently needed. In this exploratory study, we use natural language processing to extract sentiments and emotions expressed in food security-related tweets early in the pandemic in U.S. states. The emotion joy dominated in these tweets nationally, but only anger, disgust, and fear were also statistically correlated with contemporaneous food insufficiency rates reported in the Household Pulse Survey; more nuanced and statistically stronger correlations are detected within states, including a negative correlation with joy.
Keywords: Twitter sentiments; U.S. states; food insecurity; machine learning.
© 2022 The Authors. Applied Economic Perspectives and Policy published by Wiley Periodicals LLC on behalf of Agricultural & Applied Economics Association.