Latent Linguistic Motifs in Social Media Postings Resisting COVID-19 Misinformation

Social media has become a predominant source of information for many health care consumers. However, false and misleading information is a pervasive problem in this context. Specifically, health-related misinformation has become a significant public health challenge, impeding the effectiveness of public health awareness campaigns and resulting in suboptimal responsiveness to the communication of legitimate risk-related information. Little is known about the mechanisms driving the seeding and spreading of such information. In this paper, we specifically examine COVID-19 tweets which attempt to correct misinformation. We employ a mixed-methods approach comprising qualitative coding, deep learning classification, and computerized text analysis to understand the manifestation of speech acts and other linguistic variables. Results indicate significant differences in linguistic variables (e.g., positive emotion, tone, authenticity) of corrective tweets and their dissemination level. Our deep learning classifier has a macro average performance of 0.82. Implications for effective and persuasive misinformation correction efforts are discussed.