Detecting Food Insecurity

Problem

Can we identify where food-security interventions are most needed when supply chains are disrupted?

• Global food supplies can be compromised by major shocks to supply chains caused by war, natural disasters, or health crises, such as the onset of the COVID-19 pandemic.
• Surveys are one way to assess disruptions to food security, but they tend to be costly with delayed results.

Findings

Researchers analyzed Twitter posts in real-time to understand how people actually felt about their food situation and provide insights into user behavior, emotional state, and sentiment during the COVID-19 pandemic. To carry out the study, they used a dataset known as GeoCoV19, which contains hundreds of millions of pandemic-related tweets in multiple languages from all over the world.

• Using artificial intelligence and natural-language processing, they were able to separate tweets expressing concerns about food supply from those expressing relief or contentment.
• Food security-related tweets that expressed anger, disgust, or fear were strongly correlated with actual food insufficiency in certain U.S. states early in the COVID-19 pandemic.

Impact

These findings can potentially be used to develop a low-cost early warning system for planners, supply chain managers, and policymakers to detect when and where localized food security problems emerge in real-time.

Research Credit

Team

• Stephan Goetz, Connor Heaton, Muhammad Imran, Yuxuan Pan, Zheng Tian, Claudia Schmidt, Umair Qazi, Ferda Ofli, Prasenjit Mitra

Participating Department

• Agricultural Economics, Sociology, and Education

Partners

• Northeast Regional Center for Rural Development
• Penn State College of Information Sciences and Technology
• Hamad Bin Khalifa University, Qatar

Competitive Funding

• USDA NIFA (Rural Development Centers)
• Penn State College of Agricultural Sciences Institute for Sustainable Agricultural, Food, and Environmental Science (SAFES)

Federal and State Appropriations

• USDA NIFA Hatch Multistate Project PEN04633, Accession #1014522

Emerging Discoveries

Using tweets to predict real-time food shortages

April 11, 2022

The sentiments and emotions expressed in tweets on Twitter can be used in real time to assess where supply chain disruptions due to a pandemic, war or natural disaster may lead to food shortages, according to researchers at Penn State and the Hamad Bin Khalifa University in Qatar.

Published Research

Food insufficiency and Twitter emotions during a pandemic

• Goetz, S. J., Heaton, C., Imran, M., Pan, Y., Tian, Z., Schmidt, C., Qazi, U., Ofli, F., & Mitra, P. (2022). Food insufficiency and Twitter emotions during a pandemic. Applied Economic Perspectives and Policy. https://doi.org/10.1002/aepp.13258