Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Causal Graph Approach to Oppositional Narrative Analysis

Diego Revilla, Martin Fernandez-de-Retana, Lingfeng Chen, Aritz Bilbao-Jayo, Miguel Fernandez-de-Retana

TL;DR

This work proposes a graph-based framework for the detection, analysis, and classification of oppositional narratives and their underlying entities by representing narratives as entity-interaction graphs and introduces a classification pipeline that outperforms existing approaches to oppositional thinking classification task.

Abstract

Current methods for textual analysis rely on data annotated within predefined ontologies, often embedding human bias within black-box models. Despite achieving near-perfect performance, these approaches exploit unstructured, linear pattern recognition rather than modeling the structured interactions between entities that naturally emerge in discourse. In this work, we propose a graph-based framework for the detection, analysis, and classification of oppositional narratives and their underlying entities by representing narratives as entity-interaction graphs. Moreover, by incorporating causal estimation at the node level, our approach derives a causal representation of each contribution to the final classification by distilling the constructed sentence graph into a minimal causal subgraph. Building upon this representation, we introduce a classification pipeline that outperforms existing approaches to oppositional thinking classification task.

A Causal Graph Approach to Oppositional Narrative Analysis

TL;DR

This work proposes a graph-based framework for the detection, analysis, and classification of oppositional narratives and their underlying entities by representing narratives as entity-interaction graphs and introduces a classification pipeline that outperforms existing approaches to oppositional thinking classification task.

Abstract

Current methods for textual analysis rely on data annotated within predefined ontologies, often embedding human bias within black-box models. Despite achieving near-perfect performance, these approaches exploit unstructured, linear pattern recognition rather than modeling the structured interactions between entities that naturally emerge in discourse. In this work, we propose a graph-based framework for the detection, analysis, and classification of oppositional narratives and their underlying entities by representing narratives as entity-interaction graphs. Moreover, by incorporating causal estimation at the node level, our approach derives a causal representation of each contribution to the final classification by distilling the constructed sentence graph into a minimal causal subgraph. Building upon this representation, we introduce a classification pipeline that outperforms existing approaches to oppositional thinking classification task.
Paper Structure (15 sections, 7 equations, 2 figures, 4 tables, 1 algorithm)

This paper contains 15 sections, 7 equations, 2 figures, 4 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work
  3. Methodology
  4. Results
  5. Dataset
  6. Classification Performance
  7. Causal Inference and Explainability
  8. Minimal Subgraph Compression
  9. Ablations
  10. Conclusion
  11. Future Work
  12. Limitations
  13. Ethical Considerations
  14. Acknowledgments
  15. Appendix

Figures (2)

  • Figure 1: Overview of the proposed methodology. Stage 1 defines the input, which in this case consists of oppositional narratives. Stage 2 generates tokens and contextual embeddings using BERT. Stage 3 extracts the entities $V$ from the tokens and embeddings applying the Algorithm \ref{['alg:hypergraph_vertices']} (Appendix). Stage 4 produces enriched low-dimensional representations of the entities. Stage 5 constructs the adjacency matrix $A$. Stage 6 performs graph classification. Finally, the last stage presents the causal analysis.
  • Figure 2: An oppositional narrative text correctly classified as Conspiracy, with a predicted probability of 0.836, indicating high model confidence.