Date Thesis Awarded
12-2017
Access Type
Honors Thesis -- Access Restricted On-Campus Only
Degree Name
Bachelors of Science (BS)
Department
Computer Science
Advisor
James W. Deverick
Committee Members
Dr. Timothy Davis
Dr. Robert Michael Lewis
Dr. Mainak Patel
Abstract
Many news outlets report stories shown with biased undertones that mislead readers to believe one story over another about the same event. To help people delineate between liberallyand conservatively-biased news articles, we created a website which uses a recurrent neural network with long short-term memory nodes trained to identify bias found in news articles. The network achieved an F1 Score of 0.76, and is used to provide one liberally-biased article and one conservatively-biased article side-by-side for a user to read when the user searches for a specific news story
Recommended Citation
Lightfoot, Colin, "Analyzing Political Bias through a User-Friendly Interface" (2017). Undergraduate Honors Theses. William & Mary. Paper 1143.
https://scholarworks.wm.edu/honorstheses/1143
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-Share Alike 3.0 License.
