Wesley Kochell
Wesley Kochell is a junior Community Health major from Indianapolis, Indiana, on a pre-dental track. This semester, he has worked with Dr. Danny Valdez in the Center for Social and Biomedical Complexity through the Luddy School of Informatics. His research seeks to apply data mining techniques to understand the social media discourse surrounding various public health topics.
“BEWARE THE FAKE COVID-19 VACCINE”: Data mining insights into online COVID-19 vaccine misinformation
Background: Despite empirical research documenting MRNA vaccine efficacy against COVID-19, misinformation surrounding MRNA vaccine safety persists. Social media platforms, including Twitter, are one of the many avenues by which propagation of misinformation may occur.
Purpose: This study answers two research questions: (1) What themes emerge from a corpus of tweets about MRNA vaccines, and (2) Can we identify MRNA misinformation from these tweets via natural language processing (NLP).
Methods: LDA topic models, VADER sentiment analysis, Principal Components
Results: Seven themes emerge from our analysis. Most themes centered on vaccine outreach evidenced by keywords such as infection, claim, efficacy and safety. At least one thematic cluster is focused on the unfounded claims, denoted by keywords such as pain, death, brain, b***s***, bleed and killed. Thematic clusters particularly associated with MRNA vaccine misinformation appear isolated from the larger discourse.
Conclusions: The success of public health interventions depends on the ability to track and respond to misinformation. The analyses used in this study offers an option to visualize data to see and identify pockets of misinformation more easily. Our thematic analyses seemingly suggest misinformation persists on social media and is pervasive. It is likely that some misinformation in our corpus is driven by bots and not human accounts which speaks to the weaponization of social media to spread false or misleading information.
Accessibility Note: To access auto closed captions (CC) services please click on the CC icon in the bottom of the video. Manual CC are available by submitting a request for services to ATAC: (812) 856-4112 or atac@iu.edu