TY - JOUR
T1 - Analysis of social media discussions on (#)diet by blue, red, and swing states in the U.S.
AU - Karami, Amir
AU - Dahl, Alicia A.
AU - Shaw, George
AU - Valappil, Sruthi Puthan
AU - Turner-McGrievy, Gabrielle
AU - Kharrazi, Hadi
AU - Bozorgi, Parisa
N1 - Publisher Copyright:
© 2021 by the authors. Licensee MDPI, Basel, Switzerland.
PY - 2021
Y1 - 2021
N2 - The relationship between political affiliations and diet-related discussions on social media has not been studied on a population level. This study used a cost- and -time effective framework to leverage, aggregate, and analyze data from social media. This paper enhances our understanding of diet-related discussions with respect to political orientations in U.S. states. This mixed methods study used computational methods to collect tweets containing “diet” or "#diet” shared in a year, identified tweets posted by U.S. Twitter users, disclosed topics of tweets, and compared democratic, republican, and swing states based on the weight of topics. A qualitative method was employed to code topics. We found 32 unique topics extracted from more than 800,000 tweets, including a wide range of themes, such as diet types and chronic conditions. Based on the comparative analysis of the topic weights, our results revealed a significant difference between democratic, republican, and swing states. The largest difference was detected between swing and democratic states, and the smallest difference was identified between swing and republican states. Our study provides initial insight on the association of potential political leanings with health (e.g., dietary behaviors). Our results show diet discussions differ depending on the political orientation of the state in which Twitter users reside. Understanding the correlation of dietary preferences based on political orientation can help develop targeted and effective health promotion, communication, and policymaking strategies.
AB - The relationship between political affiliations and diet-related discussions on social media has not been studied on a population level. This study used a cost- and -time effective framework to leverage, aggregate, and analyze data from social media. This paper enhances our understanding of diet-related discussions with respect to political orientations in U.S. states. This mixed methods study used computational methods to collect tweets containing “diet” or "#diet” shared in a year, identified tweets posted by U.S. Twitter users, disclosed topics of tweets, and compared democratic, republican, and swing states based on the weight of topics. A qualitative method was employed to code topics. We found 32 unique topics extracted from more than 800,000 tweets, including a wide range of themes, such as diet types and chronic conditions. Based on the comparative analysis of the topic weights, our results revealed a significant difference between democratic, republican, and swing states. The largest difference was detected between swing and democratic states, and the smallest difference was identified between swing and republican states. Our study provides initial insight on the association of potential political leanings with health (e.g., dietary behaviors). Our results show diet discussions differ depending on the political orientation of the state in which Twitter users reside. Understanding the correlation of dietary preferences based on political orientation can help develop targeted and effective health promotion, communication, and policymaking strategies.
KW - Diet
KW - Health
KW - Politics
KW - Social media
KW - Text mining
UR - http://www.scopus.com/inward/record.url?scp=85105554133&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85105554133&partnerID=8YFLogxK
U2 - 10.3390/healthcare9050518
DO - 10.3390/healthcare9050518
M3 - Article
C2 - 33946659
AN - SCOPUS:85105554133
SN - 2227-9032
VL - 9
JO - Healthcare (Switzerland)
JF - Healthcare (Switzerland)
IS - 5
M1 - 518
ER -