Date of Award

8-2025

Document Type

Project

Degree Name

Master of Science in Computer Science

Department

School of Computer Science and Engineering

First Reader/Committee Chair

Salloum, Ronald

Abstract

Fact-Checker is a web application that allows users to fact-check YouTube videos. It feeds YouTube’s closed captioning transcript to a large language model (LLM) to extract claims. It then uses multiple LLMs, such as Gemini, Llama, and Claude, to verify these claims. The modular design makes it easy to change to a different LLM or model if needed. The application is built using Python for access to Application Programming Interfaces (APIs) and Streamlit as the front-end framework. The utilization of Docker and Dockerfiles enables easy distribution and deployment. It enables the application to be deployed on almost any hardware platform and accessed via a web browser. It was shown that the application is successful at identifying potential misinformation presented in YouTube videos. The dataset comprised three topics of interest — World War II, the Moon Landing, and Malaysian Airlines Flight 370 — with 20 videos collected for each topic. On the topic of World War II, 93% of the claims made across the 20 videos were labeled as Very Likely True or Likely True. The slightly lower percentages for the Moon Landing (87%) and Malaysian Airlines Flight 370 (83%) indicate that these topics may carry a higher potential for misinformation.

Download

  Contact Author

Share

COinS