Date of Award
Campus Access Thesis
Master of Science (MS)
The spread of misinformation on social media in the ongoing COVID-19 pandemic is a great concern for public health. In this study, we build a misinformation dataset by web scraping six fact-checking websites. Using a topic modeling approach, we then analyze the dataset for 8210 fact-checked articles debunked from Jan-2020 to Aug-2020. Our analysis resulted in 13 categories/trends and 35 subcategories of misinformation. Next, we utilize the output of topic modeling to train a classifier that predicts the misinformation category. The evaluation results suggest that the Multiclass Support Vector Machine (MSVM)- based classifier achieved high performance for accuracy (88%), precision (85%), recall (83%), and F-measure (82%). In addition, we also explores public health beliefs related to COVID-19 misinformation using the Health Belief Model (HBM) configuration. Finally, we discuss the implications of our findings for health and regulatory agencies and social media organizations.
Shinde, Archana, "COVID-19 and Health Misinformation: A Topology and Classification Model" (2021). Graduate Masters Theses. 758.