Social media has become predominant as a source of information for many health care consumers. However false and misleading information are a pervasive problem in this context. Specifically, during CVID-19 pandemic, misinformation has been 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. In the proposed research, we will apply our ?Pragmatics to Reveal Intent in Social Media (PRISM) framework to facilitate automated detection of intent and belief attributes underlying COVID-19 related misinformation. The PRISM framework aims to incorporate and integrate communication intent, semantics and structure of online communication to study social processes and cognitive factors underlying misinformation comprehension. Such analysis forms the foundational step towards characterization of misinformation seeding and perception in digital social settings, ultimately allowing us to develop scalable and reliable computational infrastructure that can help formulate resilient and effective dissemination approaches to negotiate misinformation spread, easing public health burden and informing policy regulations as needed.
This project enables retrospective analysis of social intercourse to facilitate our understanding of the associations between communication (content, intent, structure), cognitive biases, and social influence dynamics underlying COVID-19 related online interactions as manifested in social media. As a component of the proposed research, we will integrate methods of discourse analysis, automated text analysis, and dynamic network models to analyze electronically captured peer-to-peer communication and characterize individual intent and belief attributes at scale. By enabling deeper analysis of communication in online platforms, resulting research can help engineer compensation strategies to mitigate misinformation spread.
