Abstract
Media is an indispensable source of information and opinion, shaping the beliefs and attitudes of our society. Obviously, media portals can also provide overly biased content, e.g., by reporting on political events in a selective or incomplete manner. A relevant question hence is whether and how such a form of unfair news coverage can be exposed. This paper addresses the automatic detection of bias, but it goes one step further in that it explores how political bias and unfairness are manifested linguistically. We utilize a new corpus of 6964 news articles with labels derived from adfontesmedia.com to develop a neural model for bias assessment. Analyzing the model on article excerpts, we find insightful bias patterns at different levels of text granularity, from single words to the whole article discourse.
Highlights
Reporting news in a politically unbiased and fair manner is a key component of journalism ethics and standards
We utilize two well-known websites that address media bias, allsides.com and adfontesmedia.com, in order to create a corpus with 6964 news articles, each of which is labeled for its topic, political bias, and unfairness
We find some LIWC categories to be correlated with political bias and unfairness, such as negative emotion, focus present, and percept
Summary
Reporting news in a politically unbiased and fair manner is a key component of journalism ethics and standards. We utilize two well-known websites that address media bias, allsides.com and adfontesmedia.com, in order to create a corpus with 6964 news articles, each of which is labeled for its topic, political bias, and unfairness Based on this corpus, we devise a recurrent neural network architecture to learn classification knowledge for bias detection. We devise a recurrent neural network architecture to learn classification knowledge for bias detection We choose this network class because of its proven ability to capture semantic information at multiple levels: taking the model output for whole texts, we conduct an in-depth reverse feature analysis to explore media bias at the word, the sentence, the paragraph, and the discourse level. At levels of larger granularity, we observe that the last part of an article usually tends to be most biased and unfairest
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
