Research in this area uses Twitter and other social media data to perform surveillance and analysis of disease incidence and social factors that enable disease spread. We show that a combination of machine learning and experimental design approaches may be used to improve systems that forecast influenza by incorporating contextual knowledge. Ongoing projects include an analysis of anti-vaccine rationales and how public health agencies may better target and tailor their communications to increase vaccine uptake. Within this research stream, we have shown that Russian Twitter trolls and other spambots amplify the vaccine debate, eroding public health. This paper has been featured in over 200 separate news outlets around the world. Other papers within this same research stream examine the spread of online conspiracy theories about vaccination and effective strategies for combating misinformation and disinformation – a topic which has extensive application across multiple areas of research and practice. Our work is featured on a translational website www.socialmediaforpublichealth.org
Research on this project is supported in part by the National Institute of General Medical Sciences of the National Institutes of Health under award number R01GM114771. The content is solely the responsibility of the authors and does not necessarily represent the official views of the NIH.
