Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Reliable News or Propagandist News? A Neurosymbolic Model Using Genre, Topic, and Persuasion Techniques to Improve Robustness in Classification

Géraud Faye, Benjamin Icard, Morgane Casanova, Guillaume Gadek, Guillaume Gravier, Wassila Ouerdane, Céline Hudelot, Sylvain Gatepaille, Paul Égré

Abstract

Among news disorders, propagandist news are particularly insidious, because they tend to mix oriented messages with factual reports intended to look like reliable news. To detect propaganda, extant approaches based on Language Models such as BERT are promising but often overfit their training datasets, due to biases in data collection. To enhance classification robustness and improve generalization to new sources, we propose a neurosymbolic approach combining non-contextual text embeddings (fastText) with symbolic conceptual features such as genre, topic, and persuasion techniques. Results show improvements over equivalent text-only methods, and ablation studies as well as explainability analyses confirm the benefits of the added features. Keywords: Information disorder, Fake news, Propaganda, Classification, Topic modeling, Hybrid method, Neurosymbolic model, Ablation, Robustness

Reliable News or Propagandist News? A Neurosymbolic Model Using Genre, Topic, and Persuasion Techniques to Improve Robustness in Classification

Abstract

Among news disorders, propagandist news are particularly insidious, because they tend to mix oriented messages with factual reports intended to look like reliable news. To detect propaganda, extant approaches based on Language Models such as BERT are promising but often overfit their training datasets, due to biases in data collection. To enhance classification robustness and improve generalization to new sources, we propose a neurosymbolic approach combining non-contextual text embeddings (fastText) with symbolic conceptual features such as genre, topic, and persuasion techniques. Results show improvements over equivalent text-only methods, and ablation studies as well as explainability analyses confirm the benefits of the added features. Keywords: Information disorder, Fake news, Propaganda, Classification, Topic modeling, Hybrid method, Neurosymbolic model, Ablation, Robustness

Paper Structure

This paper contains 18 sections, 5 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Related work
  3. Datasets used
  4. Two corpora
  5. Review of published observations
  6. Genres, topics, and persuasion techniques
  7. Genres.
  8. Topics.
  9. Persuasion techniques.
  10. Neurosymbolic approach for propaganda detection
  11. Proposed architecture
  12. Evaluation methodology
  13. Results
  14. Main results
  15. Ablation studies
  16. ...and 3 more sections

Figures (5)

  • Figure 1: News genre distribution on the two corpora.
  • Figure 2: Topic distribution on the two corpora.
  • Figure 3: Mean number of persuasion techniques by article, on the two corpora.
  • Figure 4: Our hybrid architecture, combining neural features and extracted concepts.
  • Figure 5: Mean SHAP values for the Hybrid method depending on split.