Leveraging Twitter data to analyze the virality of Covid-19 tweets: a text mining approach

Abstract

Full bibliographic details must be given when referring to, or quoting from full items including the author's name, the title of the work, publication details where relevant (place, publisher, date), pagination, and for theses or dissertations the awarding institution, the degree type awarded, and the date of the award.

Factors Driving the Popularity and Virality of COVID-19 Vaccine Discourse on Twitter: Text Mining and Data Visualization Study

“…On Twitter, users can click on the “Like” icon to show appreciation for a tweet or on the “Retweet” icon to share it publicly with their followers [ 24 ]. Prior research has considered the like count of a tweet as an indicator of its popularity and the retweet count of a tweet as an indicator of its virality [ 23 , 25 ]. Drawing on these studies [ 23 , 25 ], we assessed the popularity of a tweet by the number of likes and assessed the virality of a tweet by the number of retweets.…”

“…Prior research has considered the like count of a tweet as an indicator of its popularity and the retweet count of a tweet as an indicator of its virality [ 23 , 25 ]. Drawing on these studies [ 23 , 25 ], we assessed the popularity of a tweet by the number of likes and assessed the virality of a tweet by the number of retweets. Compared with liking, retweeting is a more social behavior [ 26 ].…”

“…Research has shown that overall content usefulness and presence of efficacy information both facilitate viewing and sharing of health news articles on social media [ 26 ]. In the situation of the COVID-19 pandemic, gaps in knowledge about the new coronavirus was evident in the United States early on [ 29 ] and demand for information of practical value was expected [ 25 , 30 ]. In addition, according to the uncertainty reduction theory, to alleviate risks in crises, people intend to engage in uncertainty reduction efforts by collecting credible information and sharing with others [ 25 ].…”

“…In the situation of the COVID-19 pandemic, gaps in knowledge about the new coronavirus was evident in the United States early on [ 29 ] and demand for information of practical value was expected [ 25 , 30 ]. In addition, according to the uncertainty reduction theory, to alleviate risks in crises, people intend to engage in uncertainty reduction efforts by collecting credible information and sharing with others [ 25 ]. Nanath and Joy’s [ 25 ] text mining study revealed that the optimism and solution topic as well as the mental health topic were positive predictors of retweet counts of COVID-19–related tweets.…”

“…In addition, according to the uncertainty reduction theory, to alleviate risks in crises, people intend to engage in uncertainty reduction efforts by collecting credible information and sharing with others [ 25 ]. Nanath and Joy’s [ 25 ] text mining study revealed that the optimism and solution topic as well as the mental health topic were positive predictors of retweet counts of COVID-19–related tweets. In addition to information utility, novel content in health news has been found to increase sharing [ 26 ].…”