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

Read more

Summary

Introduction

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

Related Work
Media Bias Corpus
Media Bias Analysis
Media Bias Classification
Reverse Feature Analysis
Conclusion
Full Text
Paper version not known

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 call