The Association Between Dissemination and Characteristics of Pro-/Anti-COVID-19 Vaccine Messages on Twitter: Application of the Elaboration Likelihood Model

Abstract

Background: Messages on one's stance toward vaccination on microblogging sites may affect the reader's decision on whether to receive a vaccine. Understanding the dissemination of provaccine and antivaccine messages relating to COVID-19 on social media is crucial; however, studies on this topic have remained limited.

Objective: This study applies the elaboration likelihood model (ELM) to explore the characteristics of vaccine stance messages that may appeal to Twitter users. First, we examined the associations between the characteristics of vaccine stance tweets and the likelihood and number of retweets. Second, we identified the relative importance of the central and peripheral routes in decision-making on sharing a message.

Methods: English-language tweets from the United States that contained provaccine and antivaccine hashtags (N=150,338) were analyzed between April 26 and August 26, 2021. Logistic and generalized negative binomial regressions were conducted to predict retweet outcomes. The content-related central-route predictors were measured using the numbers of hashtags and mentions, emotional valence, emotional intensity, and concreteness. The content-unrelated peripheral-route predictors were measured using the numbers of likes and followers and whether the source was a verified user.

Results: Content-related characteristics played a prominent role in shaping decisions regarding whether to retweet antivaccine messages. Particularly, positive valence (incidence rate ratio [IRR]=1.32, P=.03) and concreteness (odds ratio [OR]=1.17, P=.01) were associated with higher numbers and likelihood of retweets of antivaccine messages, respectively; emotional intensity (subjectivity) was associated with fewer retweets of antivaccine messages (OR=0.78, P=.03; IRR=0.80, P=.04). However, these factors had either no or only small effects on the sharing of provaccine tweets. Retweets of provaccine messages were primarily determined by content-unrelated characteristics, such as the numbers of likes (OR=2.55, IRR=2.24, P<.001) and followers (OR=1.31, IRR=1.28, P<.001).

Conclusions: The dissemination of antivaccine messages is associated with both content-related and content-unrelated characteristics. By contrast, the dissemination of provaccine messages is primarily driven by content-unrelated characteristics. These findings signify the importance of leveraging the peripheral route to promote the dissemination of provaccine messages. Because antivaccine tweets with positive emotions, objective content, and concrete words are more likely to be disseminated, policymakers should pay attention to antivaccine messages with such characteristics.

Keywords: COVID-19; Twitter; antivaccine; content analysis; dissemination; elaboration likelihood model; emotional valence; infodemiology; provaccine; social media.

Figure 1

The ELM: central and peripheral routes for disseminating pro- and antivaccine tweets. ELM: elaboration likelihood model.

Figure 2

Data collection for provaccine and antivaccine tweets. This flowchart illustrates the data collection and cleaning of the final data set of vaccine stance tweets from the United States. We filtered out retweets and retained tweets from original users who had a consistent vaccine stance throughout the study periods. The green color refers to the number of provaccine tweets, and the red color refers to antivaccine tweets that remained in each step. API: application programming interface.

Figure 3

Results from logistic regressions of whether a vaccine stance message was retweeted. This figure illustrates the estimated OR associated with different characteristics of vaccine stance messages. The green color refers to provaccine tweets (N=141,782), and the red color refers to antivaccine tweets (N=8556). The horizontal line represents the 95% CI; the dot in the middle represents the estimate of the coefficient. The user-clustered sandwich variance estimator was used. OR: odds ratios.

Figure 4

Results from generalized negative binomial regressions of the retweet count. This figure illustrates the estimated IRRs associated with different characteristics of vaccine stance messages. The green color refers to provaccine tweets (N=141,782), and the red color refers to antivaccine tweets (N=8556). The horizontal line represents the 95% CI; the dot in the middle represents the estimate of the coefficient. The user-clustered sandwich variance estimator was used. Exposure was included in the model with the coefficient constrained to 1. IRR: incidence rate ratio.