Sentiment Analysis on COVID-19-Related Social Distancing in Canada Using Twitter Data

International Journal of Environmental Research and Public Health

Carol Shofiya¹  Samina Abidi¹ 

[1] Faculty of Computer Science, Dalhousie University, Halifax, NS B3H 1W5, Canada;

关键词: COVID-19;    Twitter;    social distancing;    sentimental analysis;    SentiStrength;    support vector machine;   

DOI  :  10.3390/ijerph18115993

来源: DOAJ

【 摘 要 】

Background: COVID-19 preventive measures have been an obstacle to millions of people around the world, influencing not only their normal day-to-day activities but also affecting their mental health. Social distancing is one such preventive measure. People express their opinions freely through social media platforms like Twitter, which can be shared among other users. The articulated texts from Twitter can be analyzed to find the sentiments of the public concerning social distancing. Objective: To understand and analyze public sentiments towards social distancing as articulated in Twitter textual data. Methods: Twitter data specific to Canada and texts comprising social distancing keywords were extrapolated, followed by utilizing the SentiStrength tool to extricate sentiment polarity of tweet texts. Thereafter, the support vector machine (SVM) algorithm was employed for sentiment classification. Evaluation of performance was measured with a confusion matrix, precision, recall, and F1 measure. Results: This study resulted in the extraction of a total of 629 tweet texts, of which, 40% of tweets exhibited neutral sentiments, followed by 35% of tweets showed negative sentiments and only 25% of tweets expressed positive sentiments towards social distancing. The SVM algorithm was applied by dissecting the dataset into 80% training and 20% testing data. Performance evaluation resulted in an accuracy of 71%. Upon using tweet texts with only positive and negative sentiment polarity, the accuracy increased to 81%. It was observed that reducing test data by 10% increased the accuracy to 87%. Conclusion: Results showed that an increase in training data increased the performance of the algorithm.

【 授权许可】

Unknown