TY  - JOUR
AU  - Correia, Jorge César
AU  - Ahmad, Sarmad Shaharyar
AU  - Waqas, Ahmed
AU  - Meraj, Hafsa
AU  - Pataky, Zoltan
PY  - 2024
DA  - 2024/10/11
TI  - Exploring Public Emotions on Obesity During the COVID-19 Pandemic Using Sentiment Analysis and Topic Modeling: Cross-Sectional Study
JO  - J Med Internet Res
SP  - e52142
VL  - 26
KW  - obesity
KW  - Twitter
KW  - infodemic
KW  - attitude
KW  - opinion
KW  - perception
KW  - perspective
KW  - obese
KW  - weight
KW  - overweight
KW  - social media
KW  - tweet
KW  - sentiment
KW  - topic modeling
KW  - BERT
KW  - Bidirectional Encoder Representations from Transformers
KW  - NLP
KW  - natural language processing
KW  - general public
KW  - celebrities
AB  - Background: Obesity is a chronic, multifactorial, and relapsing disease, affecting people of all ages worldwide, and is directly related to multiple complications. Understanding public attitudes and perceptions toward obesity is essential for developing effective health policies, prevention strategies, and treatment approaches. Objective: This study investigated the sentiments of the general public, celebrities, and important organizations regarding obesity using social media data, specifically from Twitter (subsequently rebranded as X). Methods: The study analyzes a dataset of 53,414 tweets related to obesity posted on Twitter during the COVID-19 pandemic, from April 2019 to December 2022. Sentiment analysis was performed using the XLM-RoBERTa-base model, and topic modeling was conducted using the BERTopic library. Results: The analysis revealed that tweets regarding obesity were predominantly negative. Spikes in Twitter activity correlated with significant political events, such as the exchange of obesity-related comments between US politicians and criticism of the United Kingdom’s obesity campaign. Topic modeling identified 243 clusters representing various obesity-related topics, such as childhood obesity; the US President’s obesity struggle; COVID-19 vaccinations; the UK government’s obesity campaign; body shaming; racism and high obesity rates among Black American people; smoking, substance abuse, and alcohol consumption among people with obesity; environmental risk factors; and surgical treatments. Conclusions: Twitter serves as a valuable source for understanding obesity-related sentiments and attitudes among the public, celebrities, and influential organizations. Sentiments regarding obesity were predominantly negative. Negative portrayals of obesity by influential politicians and celebrities were shown to contribute to negative public sentiments, which can have adverse effects on public health. It is essential for public figures to be mindful of their impact on public opinion and the potential consequences of their statements. 
SN  - 1438-8871
UR  - https://www.jmir.org/2024/1/e52142
UR  - https://doi.org/10.2196/52142
DO  - 10.2196/52142
ID  - info:doi/10.2196/52142
ER  -