Date of Award


Document Type


Degree Name

Master of Science (MS)


Computer Science

First Advisor

Jeremiah J. Onaolapo


In an era where misinformation and conspiracy theories (CTs) proliferate, this study presents an approach to understanding and categorizing CTs through the development of a detailed `family tree'. By adopting different definitions, we explore CTs as efforts to explain events through the lens of hidden, malevolent forces, distinguishing between actual conspiracies and theoretical beliefs without empirical proof. Leveraging an analysis of 1769 articles from fact-checking websites and employing Keyphrase Extraction, we compiled a dataset that led to the identification of 769 unique conspiracies. A RoBERTa-based binary classifier was developed, achieving an F1 score of 87\%, to distinguish CTs from non-CT content, demonstrating high effectiveness in identifying potential CT narratives within text corpora.

In addition, our research presents an improved process that combines various techniques such as classification, clustering (using HDBSCAN), and dimension reduction (via UMAP), along with labeling the clusters and Named Entity Recognition. This not only helps in identifying but also categorizing and expanding the family tree of CTs with newly discovered ones. This methodological innovation enables the systematic categorization and explanation of the relationships among different CTs, enhancing community understanding and providing insights into the thematic and hierarchical structure of CTs. Through this comprehensive approach, we aim to offer the academic community and the public tools for recognizing and understanding CTs, thereby fostering critical engagement with information and potentially mitigating the real-world impacts of CTs, such as those illustrated by the Pizzagate incident. This work highlights the role of informed awareness in combating the spread of unfounded conspiratorial narratives.



Number of Pages

68 p.