Abstract
Various communication and behavioral theories have been adopted to address health infodemics. However, there is no framework specially designed for social listening studies using social media data, machine learning, and natural language processing techniques. We aimed to propose a novel yet theory-based conceptual framework for infodemic research. We collected theories and models used in COVID-19 related studies published in peer-reviewed journals, ranging from health behavior, communication, to infodemic studies. These were analyzed and critiqued for their components, and we subsequently proposed a conceptual framework with a demonstration. Accordingly, we proposed our "Social Media Listening for Public Health Behavior" conceptual framework by not only integrating important attributes of existing theories, but also adding new attributes. The proposed conceptual framework can be used to better understand public discourse on social media, and can be integrated with other data analyses to gather a more comprehensive picture.