ORCID Identifier(s)

https://orcid.org/0009-0008-1436-7889

Graduation Semester and Year

Fall 2024

Document Type

Dissertation

Degree Name

Doctor of Philosophy in Computer Science

Department

Computer Science and Engineering

First Advisor

Shirin Nilizadeh

Second Advisor

Gabriela Mustata Wilson

Third Advisor

Chengkai Li

Fourth Advisor

Upendranath Chakravarthy

Abstract

Social media is now central to daily life, offering users a space to share content and opinions. However, these platforms also facilitate the spread of hate speech and misinformation, which can negatively impact public health. This dissertation develops methodologies to analyze social media data for insights that could inform health interventions. The research first examines user responses to toxic content, focusing on behavioral and emotional reactions, as well as group dynamics and bystander effects in toxic interactions. Another key focus is public opinion toward health interventions, particularly COVID-19 vaccination, using geolocated posts and analyzing factors such as race, ethnicity, and social determinants. Additionally, it explores the role of misinformation in vaccine hesitancy and considers social media as a cost-effective source for health metrics like health literacy. Key findings reveal that toxic interactions are likely to increase negative emotions and lead users to unfollow instigators. The study also observes a “bystander effect” in online settings, highlighting the potential role of social norms. Further, social media data helps identify regions that are likely to express higher vaccine hesitancy and aids in examining associations between state-level health and social composition variables with attitudes toward abortion expressed in geolocated posts. This dissertation underscores social media’s potential as a valuable data source for understanding population health dynamics.

Keywords

social media analysis, social dynamics, online toxicity, vaccine hesitancy, misinformation, public health interventions, abortion, LLM-based stance detection models

Disciplines

Applied Statistics | Artificial Intelligence and Robotics | COVID-19 | Data Science | Information Security | Maternal and Child Health | Multivariate Analysis | Other Computer Sciences | Statistical Models

License

Creative Commons Attribution 4.0 International License
This work is licensed under a Creative Commons Attribution 4.0 International License.

Available for download on Tuesday, December 16, 2025

Share

COinS