The Evolution of Public Sentiments During the COVID-19 Pandemic: Case Comparisons of India, Singapore, South Korea, the United Kingdom, and the United States

Abstract

Background Public sentiments are an important indicator of crisis response, with the need to balance exigency without adding to panic or projecting overconfidence. Given the rapid spread of the COVID-19 pandemic, governments have enacted various nationwide measures against the disease with social media platforms providing the previously unparalleled communication space for the global populations. Objective This research aims to examine and provide a macro-level narrative of the evolution of public sentiments on social media at national levels, by comparing Twitter data from India, Singapore, South Korea, the United Kingdom, and the United States during the current pandemic. Methods A total of 67,363,091 Twitter posts on COVID-19 from January 28, 2020, to April 28, 2021, were analyzed from the 5 countries with “wuhan,” “corona,” “nCov,” and “covid” as search keywords. Change in sentiments (“very negative,” “negative,” “neutral or mixed,” “positive,” “very positive”) were compared between countries in connection with disease milestones and public health directives. Results Country-specific assessments show that negative sentiments were predominant across all 5 countries during the initial period of the global pandemic. However, positive sentiments encompassing hope, resilience, and support arose at differing intensities across the 5 countries, particularly in Asian countries. In the next stage of the pandemic, India, Singapore, and South Korea faced escalating waves of COVID-19 cases, resulting in negative sentiments, but positive sentiments appeared simultaneously. In contrast, although negative sentiments in the United Kingdom and the United States increased substantially after the declaration of a national public emergency, strong parallel positive sentiments were slow to surface. Conclusions Our findings on sentiments across countries facing similar outbreak concerns suggest potential associations between government response actions both in terms of policy and communications, and public sentiment trends. Overall, a more concerted approach to government crisis communication appears to be associated with more stable and less volatile public sentiments over the evolution of the COVID-19 pandemic.

Can people hear others’ crying?: A computational analysis of help-seeking on Weibo during COVID-19 outbreak in China

“…Compared with unemotional content, retweeting ( Firdaus et al, 2018 ; Naveed et al, 2011 ) and commenting ( Burke & Develin, 2016 ) generally occur more commonly with exposure to negative emotion. The negative sentiment was also proven to be associated with higher perceived risks ( Lwin et al, 2022 ), thus significantly influencing the acceptance of policy ( Rodriguez-Sanchez et al, 2018 ) and driving the timely help from the government to ensure social stability ( Li et al, 2019 ). H1.2 : The help-seeking posts containing negative sentiment receive more retweets (H1.2a), comments (H1.2b), and have a higher chance to get assistance (H1.2c).…”

MonkeyPox2022Tweets: The First Public Twitter Dataset on the 2022 MonkeyPox Outbreak

“…The recent works in the fields of Big Data, Data Mining, and Natural Language related to Twitter data analysis [42][43][44][45][46][47][48][49][50][51][52][53][54][55][56][57] and the development of Twitter datasets [31][32][33][34][35][36][37][38][39][40][41], as discussed in Section 1, uphold the fact that Twitter datasets serve as a rich data resource for the investigation of research questions on a wide range of topics as well as for different use case scenarios. Based on studying these recent works, the following is a list of potential research questions related to the 2022 monkeypox outbreak that may be investigated by using this dataset: 1.…”

“…For instance, the Twitter dataset on music [38] has helped in the development of a context-aware music recommendation system [42], next-track music recommendations as per user personalization [43], session-based music recommendation algorithms [44], music recommendation systems based on the use of affective hashtags [45], music chart predictions [46], user curated playlists [47], sentiment analysis of music [48], listener engagement with popular songs [49], culture aware music recommendation systems [50], mining of user personalities [51], and several other applications. Similarly, the COVID-19 Twitter dataset proposed in [32] has been used for topic detection and sentiment analysis [52], language-agnostic discourse classification of tweets [53], monitoring emotions of people [54], studying the dynamics of user emotions [55], conversation analysis [56], studying the evolution of public sentiments over time [57], and several other applications.…”

The Role of Social Media Influencing Public Trust in Government During the COVID-19 Pandemic

“…Some of the successful protocols during pandemic include the development of clear guidelines for the public, the implementation of their efficient contract tracing and testing, and a reliable support for medical workforce that could treat the quarantined and infected population (Kim et al, 2021). Outbreaks were recorded to have been managed as early as March through August and gradually lessened towards December of 2020 (Lwin et al, 2022). With cooperation with businesses and media, South Korea was able to successfully detect, contain, and treat the spread in an organized manner.…”