Food insufficiency and Twitter emotions during a pandemic

Stephan J. Goetz; Connor Heaton; Muhammad Imran; Yuxuan Pan; Zheng Tian; Claudia Schmidt; Umair Qazi; Ferda Ofli; Prasenjit Mitra

doi:10.1002/aepp.13258

Food insufficiency and Twitter emotions during a pandemic

Stephan J. Goetz, Connor Heaton, Muhammad Imran, Yuxuan Pan, Zheng Tian^*, Claudia Schmidt, Umair Qazi, Ferda Ofli, Prasenjit Mitra

^*Corresponding author for this work

Qatar Computing Research Institute

Research output: Contribution to journal › Article › peer-review

12 Citations (Scopus)

Abstract

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.

Original language	English
Pages (from-to)	1189-1210
Number of pages	22
Journal	Applied Economic Perspectives and Policy
Volume	45
Issue number	2
DOIs	https://doi.org/10.1002/aepp.13258
Publication status	Published - Jun 2023

Keywords

Food insecurity
Machine learning
S
States
Twitter sentiments
U

Access to Document

10.1002/aepp.13258

Cite this

@article{c0f2abec10e34ee39d958d8ae4d26bd2,

title = "Food insufficiency and Twitter emotions during a pandemic",

abstract = "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 = "Food insecurity, Machine learning, S, States, Twitter sentiments, U",

author = "Goetz, {Stephan J.} and Connor Heaton and Muhammad Imran and Yuxuan Pan and Zheng Tian and Claudia Schmidt and Umair Qazi and Ferda Ofli and Prasenjit Mitra",

note = "Publisher Copyright: {\textcopyright} 2022 The Authors. Applied Economic Perspectives and Policy published by Wiley Periodicals LLC on behalf of Agricultural & Applied Economics Association.",

year = "2023",

month = jun,

doi = "10.1002/aepp.13258",

language = "English",

volume = "45",

pages = "1189--1210",

journal = "Applied Economic Perspectives and Policy",

issn = "2040-5790",

publisher = "John Wiley & Sons Inc.",

number = "2",

}

TY - JOUR

T1 - Food insufficiency and Twitter emotions during a pandemic

AU - Goetz, Stephan J.

AU - Heaton, Connor

AU - Imran, Muhammad

AU - Pan, Yuxuan

AU - Tian, Zheng

AU - Schmidt, Claudia

AU - Qazi, Umair

AU - Ofli, Ferda

AU - Mitra, Prasenjit

PY - 2023/6

Y1 - 2023/6

N2 - 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.

AB - 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.

KW - Food insecurity

KW - Machine learning

KW - S

KW - States

KW - Twitter sentiments

KW - U

UR - http://www.scopus.com/inward/record.url?scp=85127584221&partnerID=8YFLogxK

U2 - 10.1002/aepp.13258

DO - 10.1002/aepp.13258

M3 - Article

AN - SCOPUS:85127584221

SN - 2040-5790

VL - 45

SP - 1189

EP - 1210

JO - Applied Economic Perspectives and Policy

JF - Applied Economic Perspectives and Policy

IS - 2

ER -

Food insufficiency and Twitter emotions during a pandemic

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this