Exploratory Analysis of COVID-19 Related Tweets in North America to Inform Public Health Institutes

Abstract

Social media is a rich source where we can learn about people's reactions to social issues. As COVID-19 has significantly impacted on people's lives, it is essential to capture how people react to public health interventions and understand their concerns. In this paper, we aim to investigate people's reactions and concerns about COVID-19 in North America, especially focusing on Canada. We analyze COVID-19 related tweets using topic modeling and aspect-based sentiment analysis, and interpret the results with public health experts. We compare timeline of topics discussed with timing of implementation of public health interventions for COVID-19. We also examine people's sentiment about COVID-19 related issues. We discuss how the results can be helpful for public health agencies when designing a policy for new interventions. Our work shows how Natural Language Processing (NLP) techniques could be applied to public health questions with domain expert involvement.

Tracking patients healthcare experiences during the COVID-19 outbreak: Topic modeling and sentiment analysis of doctor reviews

“…It has been found that these sites and platforms contain a high volume of rumors and misinformation regarding the COVID-19 pandemic that has become a challenging task for major social media outlets (Convertino, 2020). In the past, several attempts were made to analyze social media data to measure public perceptions regarding the COVID-19 disease outbreak (Lwin et al, 2020;Zhao et al, 2020;Dong et al, 2020;Chen et al, 2020a;Xue et al, 2020a;Chen et al, 2020b;Li et al, 2020;Zhu et al, 2020;Yin et al, 2020;Jang et al, 2020;Ordun et al, 2020a;Saleh et al, 2020;Hung et al, 2020;Stokes et al, 2020). Our research can further add to this literature by showing that online data mining can provide speedy insights into public perceptions and opinions.…”

“…Yin et al (2020) proposed a new method to detect important topics and sentiment dynamics due to the COVID-19 crisis from social media posts. Jang et al (2020) analyzed Twitter data regarding the COVID-19 outbreak using topic modeling and aspect-based sentiment analysis. Moreover, the current study analyzed topic trends changes with the time during the pandemic.…”

“…We first divide ODRs into three different time slices, e.g., Feb 01-April 30, May 01-July 31, Aug 01-Oct 31. Next, we measure a mean vector θ for ODRs for each time slice as presented in (Jang et al, 2020). Referring to the mean vector θ for each time slice, we plot graphs of health-related topics over time, as presented in Figure 4-6.…”

Detecting Topic and Sentiment Trends in Physician Rating Websites: Analysis of Online Reviews Using 3-Wave Datasets

“…Based on the high-frequency PORs-based keyword analysis, knowledge about the issues and opinions of PRW users can be collected at different stages. Studies have shown that people interest in various risk diseases on social media has been related to recent news and global events [ 26 ].…”

“…The current study will only present several examples on COVID-19. Jang, et al [ 26 ] applied topic modeling to investigate COVID-19–related themes using Twitter data in North America. Zhao, Cheng, Yu and Xu [ 1 ] identified hot topics using Sina Microblog data related to COVID-19 in China.…”