Public Attitudes during the Second Lockdown: Sentiment and Topic Analyses using Tweets from Ontario, Canada (Preprint)
International journal of public health(2021)
摘要
BACKGROUND
The COVID-19 pandemic has continued for over a year and caused a significant number of cases and deaths in Canada and around the world. Governments worldwide have implemented lockdowns and other interventions to reduce the transmission.
OBJECTIVE
To explore sentiments for pre-specified topics using tweets from Ontario, Canada, during its second wave and identify any correlation between public attitude and government policy and cases.
METHODS
Tweets were collected from December 5, 2020, to March 6, 2021, with locations in Toronto and Ottawa, excluding public health, political organizations and figures. Dates of vaccine-related events and COVID-19 policy changes were collected from each public health unit in Ontario within the same period. The daily number of COVID-19 cases was retrieved directly from the Ontario provincial government’s public health database within the same time period. Valence Aware Dictionary and sEntiment Reasoner (VADER) were used to calculate daily and average sentiment compound scores for topics and keywords identified from preliminary data exploration using unsupervised topic modelling.
RESULTS
Between December 5, 2020, and March 6, 2021, the average sentiment compound score for each topic appeared to be slightly positive, while the daily sentiment compound scores varied greatly between positive and negative emotions for each topic. Positive sentiments were mainly about holiday wishes and support for healthcare works and each other, whereas negative sentiments were largely associated with frustrations and blame on political leaders.
CONCLUSIONS
The exploratory results have shown a slightly positive sentiment on average during the second wave of the COVID-19 pandemic in Ontario, along with six topics. Our research has also demonstrated a possible social listening approach to identify what the public sentiments and opinions are in a timely manner using a combination of quantitative and qualitative methods.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要