Patterns of Media Use, Strength of Belief in COVID-19 Conspiracy Theories, and the Prevention of COVID-19 From March to July 2020 in the United States: Survey Study

Abstract

Background: Holding conspiracy beliefs regarding the COVID-19 pandemic in the United States has been associated with reductions in both actions to prevent the spread of the infection (eg, mask wearing) and intentions to accept a vaccine when one becomes available. Patterns of media use have also been associated with acceptance of COVID-19 conspiracy beliefs. Here we ask whether the type of media on which a person relies increased, decreased, or had no additional effect on that person's COVID-19 conspiracy beliefs over a 4-month period.

Objective: We used panel data to explore whether use of conservative and social media in the United States, which were previously found to be positively related to holding conspiracy beliefs about the origins and prevention of COVID-19, were associated with a net increase in the strength of those beliefs from March to July of 2020. We also asked whether mainstream news sources, which were previously found to be negatively related to belief in pandemic-related conspiracies, were associated with a net decrease in the strength of such beliefs over the study period. Additionally, we asked whether subsequent changes in pandemic conspiracy beliefs related to the use of media were also related to subsequent mask wearing and vaccination intentions.

Methods: A survey that we conducted with a national US probability sample in March of 2020 and again in July with the same 840 respondents assessed belief in pandemic-related conspiracies, use of various types of media information sources, actions taken to prevent the spread of the disease and intentions to vaccinate, and various demographic characteristics. Change across the two waves was analyzed using path analytic techniques.

Results: We found that conservative media use predicted an increase in conspiracy beliefs (β=.17, 99% CI .10-.25) and that reliance on mainstream print predicted a decrease in their belief (β=-.08, 99% CI -.14 to -.02). Although many social media platforms reported downgrading or removing false or misleading content, ongoing use of such platforms by respondents predicted growth in conspiracy beliefs as well (β=.072, 99% CI .018-.123). Importantly, conspiracy belief changes related to media use between the two waves of the study were associated with the uptake of mask wearing and changes in vaccination intentions in July. Unlike other media, use of mainstream broadcast television predicted greater mask wearing (β=.17, 99% CI .09-.26) and vaccination intention (β=.08, 95% CI .02-.14), independent of conspiracy beliefs.

Conclusions: The findings point to the need for greater efforts on the part of commentators, reporters, and guests on conservative media to report verifiable information about the pandemic. The results also suggest that social media platforms need to be more aggressive in downgrading, blocking, and counteracting claims about COVID-19 vaccines, claims about mask wearing, and conspiracy beliefs that have been judged problematic by public health authorities.

Keywords: COVID-19; United States; belief; broadcast news media; conservative media; conspiracy beliefs; infodemic; intention; mask wearing; misinformation; prevention; print news media; social media; vaccination.

Figure 1

Standardized predictors of conspiracy beliefs in March and again in July with all coefficients falling within 99% CIs, except for social media and conspiracy beliefs in March.

Figure 2

Standardized relations between media use in March and subsequent conspiracy beliefs and action taken to prevent spread of COVID infection in July. All paths within 99% CIs, except between social media and conspiracy beliefs in March, which excluded zero with a 95% CI.

Figure 3

Standardized relations between media use in March and conspiracy beliefs and vaccine intentions in July. All paths within 99% CIs, except between social media and conspiracy beliefs in March and July, which excluded zero at the 95% CI.