Comparing tweet sentiments in megacities using machine learning techniques: In the midst of COVID-19. (September 2021)

• Record Type: Journal Article
• Authors: Yao, Zhirui; Yang, Junyan; Liu, Jialin; Keith, Michael; Guan, ChengHe
• Is Part Of: Cities. Volume 116(2021)
• Publication Date: 2021-09
• Subjects: COVID-19 -- Tweet sentiments -- Machine learning -- Megacities -- Quarantine policy measures; City planning -- Periodicals; Urban policy -- Periodicals; 711.4
• DOI: 10.1016/j.cities.2021.103273
• Languages: English
• ISSNs: 0264-2751

Abstract

Abstract: COVID-19 was announced by the World Health Organization as a pandemic on March 11, 2020. Not only has COVID-19 struck the economy and public health, but it also has deep influences on people's feelings. Twitter, as an active social media, is a great database where we can investigate people's sentiments during this pandemic. By conducting sentiment analysis on Tweets using advanced machine learning techniques, this study aims to investigate how public sentiments respond to the pandemic from March 2 to May 21, 2020 in New York City, Los Angeles, London, and another six global mega-cities. Results showed that across cities, negative and positive Tweet sentiment clustered around mid-March and early May, respectively. Furthermore, positive sentiments of Tweets from New York City and London were positively correlated with stricter quarantine measures, although this correlation was not significant in Los Angeles. Meanwhile, Tweet sentiments of all three cities did not exhibit a strong correlation with new cases and hospitalization. Last but not least, we provide a qualitative analysis of the reasons behind differences in correlations shown above, along with a discussion of the polarizing effect of public policies on Tweet sentiments. Thus, the results of this study imply that Tweet sentiment is more sensitive to quarantine orders than reported statistics of COVID-19, especially in populous megacities where public transportation is heavily relied upon, which calls for prompt and effective quarantine measures during contagious disease outbreaks. Highlights: Machine learning techniques analyze links between public sentiment and lockdown policies. Tweet sentiment presents positive correlations between restricted policies and numbers of confirmed cases/hospitalization. Quarantine policies could polarize sentiments presented on social media.