Fine-Grained Analysis of Propaganda in News Articles
This work addresses the need for more precise and interpretable propaganda detection in news articles, though it is incremental as it builds on existing detection methods by adding granularity.
The authors tackled the problem of noisy document-level labels and lack of explainability in propaganda detection by proposing a fine-grained analysis task to detect propaganda techniques at the fragment level, creating a manually annotated corpus with eighteen techniques and a novel multi-granularity neural network that outperformed BERT-based baselines.
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.