Fine-Grained Analysis of Propaganda in News Article

By Giovanni Da San Martino, Seunghak Yu, Alberto Barrón-Cedeño, Rostislav Petrov, Preslav Nakov. Conference on Empirical Methods in Natural Language Processing, 2019

398 citations recorded by the source corpus.

Propaganda aims at influencing people’s mindset with the purpose of advancing a specific agenda. Previous work has addressed propaganda detection at 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 fragment level with eighteen propaganda techniques and 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.

Subfields: Artificial Intelligence, Sociology and Political Science

View Paper: https://www.semanticscholar.org/paper/a12d22ff91ce159a0d3558ed5aaed115115beabd

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Sociology and Political Science

Citations in the corpus

ToxCCIn: Toxic Content Classification with Interpretability (2021, methodology): “We follow the ad-hoc evaluation metrics which are introduced in Da San Martino et al. (2019) and utilized in SemEval 2021 Task 52 – Span Detection Precision (SD-P), Recall (SD-R), and F1 (SD-F1).”
Findings of the NLP4IF-2019 Shared Task on Fine-Grained Propaganda Detection (2019, methodology): “ the minimal fragments related to a technique instead of ﬂagging entire arguments. The most relevant related work is our own, which is published in parallel to this paper at EMNLP-IJCNLP 2019 (Da San Martino et al., 2019) and describes a corpus that is a subset of the one used for this shared task. ”
Transformer models for text-based emotion detection: a review of BERT-based approaches (2021, background): “Their work could be separated into two viz., the SLC and Fragment Level Classification (FLC) (Da San Martino et al. 2019).”
A Survey on Computational Propaganda Detection (2020, methodology): “In particular, Da San Martino et al. [ 2019b ] proposed a dataset with assets that previously available resources lacked.”
Faking Fake News for Real Fake News Detection: Propaganda-Loaded Training Data Generation (2022, methodology): “First, about 33% of the articles used propaganda techniques to convince the audience that the fake information was actually authentic, and these techniques often involve the use of emotion-triggering language or logical fal-lacies (Da San Martino et al., 2019) to increase the impact on the reader.”
SemEval-2020 Task 11: Detection of Propaganda Techniques in News Articles (2020, methodology): “The training and the development part of the PTC-SemEval20 corpus are the same as the training and the testing datasets described in (Da San Martino et al., 2019b).”