Interpretable Propaganda Detection in News Articles

TL;DR

This paper presents an interpretable approach for detecting propaganda in news articles by combining descriptive deception features with pre-trained language models, achieving state-of-the-art results.

Contribution

It introduces a novel set of interpretable features for propaganda detection and demonstrates their effectiveness when integrated with pre-trained language models.

Findings

Interpretable features improve detection accuracy.

Combining features with language models yields state-of-the-art performance.

Features help explain the use of deception techniques.

Abstract

Online users today are exposed to misleading and propagandistic news articles and media posts on a daily basis. To counter thus, a number of approaches have been designed aiming to achieve a healthier and safer online news and media consumption. Automatic systems are able to support humans in detecting such content; yet, a major impediment to their broad adoption is that besides being accurate, the decisions of such systems need also to be interpretable in order to be trusted and widely adopted by users. Since misleading and propagandistic content influences readers through the use of a number of deception techniques, we propose to detect and to show the use of such techniques as a way to offer interpretability. In particular, we define qualitatively descriptive features and we analyze their suitability for detecting deception techniques. We further show that our interpretable features can be easily combined with pre-trained language models, yielding state-of-the-art results.