Automating Political Bias Prediction

by   Felix Biessmann, et al.

Every day media generate large amounts of text. An unbiased view on media reports requires an understanding of the political bias of media content. Assistive technology for estimating the political bias of texts can be helpful in this context. This study proposes a simple statistical learning approach to predict political bias from text. Standard text features extracted from speeches and manifestos of political parties are used to predict political bias in terms of political party affiliation and in terms of political views. Results indicate that political bias can be predicted with above chance accuracy. Mistakes of the model can be interpreted with respect to changes of policies of political actors. Two approaches are presented to make the results more interpretable: a) discriminative text features are related to the political orientation of a party and b) sentiment features of texts are correlated with a measure of political power. Political power appears to be strongly correlated with positive sentiment of a text. To highlight some potential use cases a web application shows how the model can be used for texts for which the political bias is not clear such as news articles.


page 1

page 2

page 3

page 4


A Machine Learning Pipeline to Examine Political Bias with Congressional Speeches

Computational methods to model political bias in social media involve se...

Political representation bias in DBpedia and Wikidata as a challenge for downstream processing

Diversity Searcher is a tool originally developed to help analyse divers...

The Self-Perception and Political Biases of ChatGPT

This contribution analyzes the self-perception and political biases of O...

Inference of Media Bias and Content Quality Using Natural-Language Processing

Media bias can significantly impact the formation and development of opi...

Relationship between the visibility of political leaders during campaign and the outcome in general elections. A case study for Spain

In this article, the authors find the evidence that media coverage consi...

Text-Based Ideal Points

Ideal point models analyze lawmakers' votes to quantify their political ...

Machine Learning and Statistical Approaches to Measuring Similarity of Political Parties

Mapping political party systems to metric policy spaces is one of the ma...

Please sign up or login with your details

Forgot password? Click here to reset