Date of Award

12-31-2021

Document Type

Campus Access Thesis

Degree Name

Master of Science (MS)

Department

Information Technology

First Advisor

Romilla Syed

Second Advisor

Atreya Chakraborty

Third Advisor

Lucia Silva-Gao

Abstract

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.

Comments

Free and open access to this Campus Access Thesis is made available to the UMass Boston community by ScholarWorks at UMass Boston. Those not on campus and those without a UMass Boston campus username and password may gain access to this thesis through resources like Proquest Dissertations & Theses Global or through Interlibrary Loan. If you have a UMass Boston campus username and password and would like to download this work from off-campus, click on the "Off-Campus UMass Boston Users" link above.

Download
Off-Campus UMass Boston Users

Share

COinS