KnowBias: Detecting Political Polarity in Long Text Content

TL;DR

This paper presents KnowBias, a method for detecting political bias in long texts by adapting models trained on tweets, using a two-step neutral sentence removal process to improve accuracy.

Contribution

It introduces a novel two-step classification approach that enhances bias detection in long texts by addressing opinion concentration differences from tweet-based training.

Findings

Improved accuracy in bias detection on articles using the proposed method.

Neutral sentence removal aligns opinion concentration between tweets and articles.

Universal sentence encoders alone are insufficient for domain adaptation.

Abstract

We introduce a classification scheme for detecting political bias in long text content such as newspaper opinion articles. Obtaining long text data and annotations at sufficient scale for training is difficult, but it is relatively easy to extract political polarity from tweets through their authorship. We train on tweets and perform inference on articles. Universal sentence encoders and other existing methods that aim to address this domain-adaptation scenario deliver inaccurate and inconsistent predictions on articles, which we show is due to a difference in opinion concentration between tweets and articles. We propose a two-step classification scheme that uses a neutral detector trained on tweets to remove neutral sentences from articles in order to align opinion concentration and therefore improve accuracy on that domain. Our implementation is available for public use at https://knowbias.ml.