"It Happened to Me and It's Serious": Conditional Indirect Effects of Infection Severity Narrated in Testimonial Tweets on COVID-19 Prevention

Abstract

The health crisis caused by COVID-19 resulted in societal breakdowns around the world. Our research is based on determining which features of testimonial messages are most relevant in increasing persuasive impact. An online experiment with a 2 (severity infection narrative: low vs. high) × 2 (infection target: narrative's protagonist vs. protagonist's father) between-subject factorial design was carried out. Young people between 18 and 28 years (N = 278) were randomly assigned to one of the four experimental conditions, where they were asked to read a narrative message in the form of a Twitter thread describing a COVID-19 infection (with mild or severe symptoms) that affected either the protagonist of the message (a 23-year-old young person) or their father. After reading the narrative message, the mediating and dependent variables were evaluated. A message describing a severe COVID-19 infection affecting their protagonist to increase the perception of personal risk increased the persuasive impact through an increase in cognitive elaboration and a reduction in reactance. Our study highlights that creating persuasive messages based on social media targeted at young people that describe a careless behavior resulting in a severe COVID-19 infection can be an appropriate strategy for designing prevention campaigns.

Keywords: COVID-19; Twitter; cognitive processes; health communication; narrative persuasion; testimonial messages.

Figure 1

Hypothesized moderated serial–parallel mediation model.

Figure 2

Moderating effect of infection target on the relationship between the severity of the symptoms described in the Twitter narrative and the perceived severity of the infection.

Figure 3

Results of the moderated serial–parallel mediation model (H5). The figures show the non-standardized regression coefficients, B. The dashed line represents non-significant coefficients. + p a 0.10, * p < 0.05, ** p < 0.01, *** p < 0.001. (a) Dependent variable: perceived personal risk of COVID-19 infection. (b) Dependent variable: perceived severity of COVID-19. (c) Dependent variable: protective behavioral intent against COVID-19.

Figure 3

Results of the moderated serial–parallel mediation model (H5). The figures show the non-standardized regression coefficients, B. The dashed line represents non-significant coefficients. + p a 0.10, * p < 0.05, ** p < 0.01, *** p < 0.001. (a) Dependent variable: perceived personal risk of COVID-19 infection. (b) Dependent variable: perceived severity of COVID-19. (c) Dependent variable: protective behavioral intent against COVID-19.