Publication Date

Spring 2023

Degree Type

Master's Project

Degree Name

Master of Science (MS)


Computer Science

First Advisor

Katerina Potika

Second Advisor

Genya Ishigaki

Third Advisor

William Andreopoulos


political bias classification, news summarization, news aggregation, transformers, language models, automation


Political polarization is on the rise in the US, driven in large part by divisive news that goes viral on the Internet. Specifically, many media outlets use slanted language and publish misinformation in order to drive user traffic and engagement. Almost 80% of US citizens get their news from online sources, but there is a lack of public safeguards against biased news. A large amount of news is published online every day by media organizations, and it is impossible to manually analyze this amount of data. There is a clear need for automated, public-facing solutions in the current political climate that can detect and classify political bias in news. Classifying biased news is a difficult task due to the complexity and nuance of political bias and ideology. Recently, transformer-based deep learning models have shown promising results in this task.

In this project, we experiment with state-of-the-art models in text classification to classify political bias in news. Additionally, we provide a comparative analysis of the best-performing models for news summarization. Moreover, we develop and release "The Bias Report", a fully automated, cloud-based News Aggregator application that uses the best-performing models in order to classify political bias and summarize news.