Their findings show a consistent negative sentiment towards topics related to the spread and growth of COVID-19, origin of virus, political perspectives, and racial discrimination, whereas sentiments toward topics associated with preventive measures and treatments, economic impacts, government implementations, healthcare industry changed from negative to positive. collected 13.9 million English tweets posted by individuals between January 1 and May 9, 2020. Furthermore, Boon-Itt and Skunkan found topics changed over time, but negative sentiments persisted when analyzing almost 11 million English tweets from December 13, 2019, to Ma. For example, Abd-Alrazaq et al identified 10 themes with positive sentiments and two topics with negative sentiments from 2.8 million English tweets between February 2 and Ma. Scholars have conducted various topic modelling and sentiment analysis to understand public concerns or attitudes toward the pandemic and public health measures, such as mask wearing, handwashing, travel restrictions, and lockdowns since the early pandemic. Understanding public discourses and sentiments from social media data has been critical for researchers and decision makers since it correlates with our behaviours that help or fail to eliminate the COVID-19 infections. Therefore, social media data, such as tweets, have become even more important in health research associated with the current pandemic. During this global crisis, when people have been forced to stay at home and connect virtually, social media platforms have played an increasingly significant role in communications now more than ever before.
In Canada, it has led to over 1 million positive cases and caused more than 24,000 deaths. The Coronavirus disease (COVID-19) pandemic has persisted for more than a year and resulted in over 141 million infections with over 3 million deaths worldwide. Our research has also demonstrated a social listening approach to identify what the public sentiments and opinions are in a timely manner. The average sentiment compound score for each topic appeared to be slightly positive, yet the daily sentiment compound scores varied greatly between positive and negative emotions for each topic.Ĭonclusion: Our study results have shown a slightly positive sentiment on average during the second wave of the COVID-19 pandemic in Ontario, along with six topics. Results: Vaccine, pandemic, business, lockdown, mask, and Ontario were six topics identified from the unsupervised topic modelling. VADER was used to calculate daily and average sentiment compound scores for topics identified. Latent Dirichlet Allocation was used for unsupervised topic modelling. The daily number of COVID-19 cases was retrieved from the Ontario provincial government’s public health database. Dates of vaccine-related events and policy changes were collected from public health units in Ontario. Methods: Tweets were collected from December 5, 2020, to March 6, 2021, excluding non-individual accounts. Objective: This study aimed to explore topics and sentiments using tweets from Ontario, Canada, during the second wave of the COVID-19 pandemic. 3Faculty of Science, University of Waterloo, Waterloo, ON, Canada.2Systems Design Engineering, University of Waterloo, Waterloo, ON, Canada.1School of Public Health SciencesUniversity of Waterloo, Waterloo, ON, Canada.Shu-Feng Tsao 1, Alexander MacLean 2, Helen Chen 1, Lianghua Li 3, Yang Yang 1 and Zahid Ahmad Butt 1*
0 kommentar(er)
