Understanding the Changes in Positive and Negative Sentiments in the Discourse of the COVID-19 Pandemic in Alberta

• Author / Creator

  Tchoh, Bennett Kuwan

• The severe acute respiratory syndrome caused by the SARS coronavirus was declared a pandemic in March 2020 by the World Health Organisation. Alberta as other provinces and countries had to face the challenge of fighting this syndrome that caused what is commonly known as the COVID-19 pandemic. The measures put in place by the government officials to fight the pandemic brought about big changes to the lives of Albertans. This study sought to explore the discourse that happened online about the COVID-19 pandemic in Alberta. One might expect that the discourse will change with changes in the gravity of the pandemic. But is this the case? Using tweets scraped from Twitter, the relationships between scores of positive and negative sentiments in these tweets and the number of patients in ICU, wave of the pandemic, mentions of oneself and people identified with (Us pronouns) and mentions of the other and people not identified with (Them pronouns) was explored using visualisations and statistical analysis tools. Three methods of measuring sentiments were used and the methods compared. Results showed that the discourse on the pandemic became less positive as we moved from the first to the fourth wave. A multiple linear regression showed that the best predictors of the sentiment score of the discourse was the wave of the pandemic and the use of Them pronouns. Comparison of the sentiment measuring methods suggested that the changes in the use of positive and negative words are not accompanied by a proportional change in the sentiment in the discourse. As expected, the number of patients in ICU correlated negatively with positive sentiment scores and positively negative sentiment scores. Unlike expected, the use of the Us and Them pronouns had similar correlations in magnitude and direction with sentiment scores. The findings from this study provide a better understanding of the changes in the sentiments of the discourse of the COVID-19 pandemic in Alberta and brings to light the importance of assessing the validity of measuring instruments and methods.

• Subjects / Keywords

  • Sentiment analysis
  • Twitter
  • COVID-19
  • Alberta

• Graduation date

  Spring 2024

• Type of Item

  Thesis

• Degree

  Master of Arts

• DOI

  https://doi.org/10.7939/r3-ghqn-nw90

• License

  This thesis is made available by the University of Alberta Libraries with permission of the copyright owner solely for non-commercial purposes. This thesis, or any portion thereof, may not otherwise be copied or reproduced without the written consent of the copyright owner, except to the extent permitted by Canadian copyright law.