Understanding public perception of coronavirus disease 2019 (COVID-19) social distancing on Twitter

Abstract

Objective: Social distancing policies are key in curtailing severe acute respiratory coronavirus virus 2 (SARS-CoV-2) spread, but their effectiveness is heavily contingent on public understanding and collective adherence. We studied public perception of social distancing through organic, large-scale discussion on Twitter.

Design: Retrospective cross-sectional study.

Methods: Between March 27 and April 10, 2020, we retrieved English-only tweets matching two trending social distancing hashtags, #socialdistancing and #stayathome. We analyzed the tweets using natural language processing and machine-learning models, and we conducted a sentiment analysis to identify emotions and polarity. We evaluated the subjectivity of tweets and estimated the frequency of discussion of social distancing rules. We then identified clusters of discussion using topic modeling and associated sentiments.

Results: We studied a sample of 574,903 tweets. For both hashtags, polarity was positive (mean, 0.148; SD, 0.290); only 15% of tweets had negative polarity. Tweets were more likely to be objective (median, 0.40; IQR, 0-0.6) with ~30% of tweets labeled as completely objective (labeled as 0 in range from 0 to 1). Approximately half of tweets (50.4%) primarily expressed joy and one-fifth expressed fear and surprise. Each correlated well with topic clusters identified by frequency including leisure and community support (ie, joy), concerns about food insecurity and quarantine effects (ie, fear), and unpredictability of coronavirus disease 2019 (COVID-19) and its implications (ie, surprise).

Conclusions: Considering the positive sentiment, preponderance of objective tweets, and topics supporting coping mechanisms, we concluded that Twitter users generally supported social distancing in the early stages of their implementation.

Fig. 1.

Word cloud of top 200 words.

Fig. 2.

Sentiment analysis for all tweets and stratified by tweets with the hashtag #socialdistancing and #stayathome. Comparison between the two hashtags is done using χ² testing. Bonferroni correction was used to define statistical significance at a threshold of P = .01 (0.05/n, where n = 5 since 5 comparisons were completed).

Fig. 3.

Subjectivity analysis for all tweets. Complete objectivity are defined as 0 and complete subjectivity are defined as 1.

Fig. 4.

Emotion analysis for all tweets and stratified by tweets with the hashtag #socialdistancing and #stayathome. Comparison between the two hashtags is done using χ² testing. Bonferroni correction was used to define statistical significance at a threshold of P = .008 (0.05/n, where n = 6 since 6 comparisons were completed).