Fine-Grained Analysis of Propaganda in News Articles

TL;DR

This paper introduces a fine-grained approach to detect propaganda techniques within news articles, creating a new annotated corpus and a neural network model that outperforms existing baselines.

Contribution

It presents a novel task of fragment-level propaganda detection, a new annotated dataset, and a multi-granularity neural network model for improved detection accuracy.

Findings

The proposed model outperforms BERT-based baselines.

Created a manually annotated corpus with 18 propaganda techniques.

Introduced a new evaluation measure for fine-grained propaganda analysis.

Abstract

Propaganda aims at influencing people's mindset with the purpose of advancing a specific agenda. Previous work has addressed propaganda detection at the document level, typically labelling all articles from a propagandistic news outlet as propaganda. Such noisy gold labels inevitably affect the quality of any learning system trained on them. A further issue with most existing systems is the lack of explainability. To overcome these limitations, we propose a novel task: performing fine-grained analysis of texts by detecting all fragments that contain propaganda techniques as well as their type. In particular, we create a corpus of news articles manually annotated at the fragment level with eighteen propaganda techniques and we propose a suitable evaluation measure. We further design a novel multi-granularity neural network, and we show that it outperforms several strong BERT-based baselines.