Investigating Bias in Newspaper Articles through Natural Language Processing
The project, mentored by Jason Cho and advised by Professor Eric Meyer, focuses on automatic bias detection in newspaper articles. It involves recognizing similar article topics and detecting bias using tools like OpenNLP and Python NLTK. The endeavor aims to uncover words correlated with bias and analyze their impact on overall bias in articles.
Download Presentation
Please find below an Image/Link to download the presentation.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author. Download presentation by click this link. If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.
E N D
Presentation Transcript
PURE Learning Plan Richard Lee, James Chen,
Project Overview Mentored by PhD candidate Jason Cho Advice from Professor Eric Meyer of the University of Illinois Department of Journalism Project in automatic bias-detection in newspaper articles Split into two parts: o Similar article topic recognition Easier, but less interesting o Automatic bias detection Harder, but more interesting
What Have We Learned? This is a very, very difficult problem. Project involves a variety of fields, including computer science, English, linguistics, mathematics, journalism, etc. Relatively unique problem, no thorough solution has been attempted/researched Similar research done, such as sarcasm detection, bias research (linguistics), etc.
Getting Up to Speed Tools OpenNLP, Python NLTK Stanford NLP Toolkit Papers Shedding (a Thousand Points of) Light on Biased Language Recognizing stances in online debates Extracting opinion targets in a single-and cross-domain setting with conditional random fields
Ideas Investigating words that have a high correlation with bias, and seeing if the presence of them indicate bias Take presumably biased articles, use named- entity recognition to parse relevant sentences (eg, all sentences with "Obama" present) Use a combination of word-counting, part-of- speech tagging, and word sentiment determination to aggregate overall bias.
