# A Counterfactual Graph Approach to Oppositional Narrative Analysis

arXiv: https://arxiv.org/abs/2603.06135 · HTML: https://mlsanity.com/paper/2603.06135/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 40 references that are in the map.
- First posted on arXiv 6 Mar 2026.

## Builds on (most cited first, 16 of 16)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [Heterogeneous Graph Transformer](https://mlsanity.com/paper/2003.01332/) (2020)
- [Span-based Joint Entity and Relation Extraction with Transformer Pre-training](https://mlsanity.com/paper/1909.07755/) (2019)
- [FactGraph: Evaluating Factuality in Summarization with Semantic Graph Representations](https://mlsanity.com/paper/2204.06508/) (2022)
- [CycleGT: Unsupervised Graph-to-Text and Text-to-Graph Generation via Cycle Training](https://mlsanity.com/paper/2006.04702/) (2020)
- [A Graph Neural Network Framework for Causal Inference in Brain Networks](https://mlsanity.com/paper/2010.07143/) (2020)
- [Entity Framing and Role Portrayal in the News](https://mlsanity.com/paper/2502.14718/) (2025)
- [Graph Neural Networks for Protein-Protein Interactions -- A Short Survey](https://mlsanity.com/paper/2404.10450/) (2024)
- [What distinguishes conspiracy from critical narratives? A computational analysis of oppositional discourse](https://mlsanity.com/paper/2407.10745/) (2024)
- [Causal invariant geographic network representations with feature and structural distribution shifts](https://mlsanity.com/paper/2503.19382/) (2025)
- [Causal GNNs: A GNN-Driven Instrumental Variable Approach for Causal Inference in Networks](https://mlsanity.com/paper/2409.08544/) (2024)
- [Beyond LLMs: A Linguistic Approach to Causal Graph Generation from Narrative Texts](https://mlsanity.com/paper/2504.07459/) (2025)
- [Individual Treatment Effect: Prediction Intervals and Sharp Bounds](https://mlsanity.com/paper/2506.07469/) (2025)

## Abstract (arXiv)

Distinguishing legitimate critical speech from coordinated conspiracy narratives is a pressing challenge for the integrity of the online information ecosystem, yet prevailing approaches rely on labeled entity roles and rigid predefined schemas that fail to capture the diffuse and context-dependent nature of participation in such narratives. We propose a modular framework that extracts an entity-interaction graph directly from narratives and reasons over it for classification, without depending on annotated node-level labels. Our pipeline enumerates candidate entity spans from a domain-adapted BERT encoder and learns a bipartite graph structure, which is then classified with a Heterogeneous Graph Transformer. To make predictions interpretable, we cast the graph as a hypergraph and apply a counterfactual distillation procedure that estimates the Individual Treatment Effect of each node, pruning extraneous entities to recover a minimal predictive subgraph. On the standard PAN Oppositional Narratives benchmark, our model achieves a macro F1-score of 0.93 and an MCC of 0.84, reaching state-of-the-art performance with roughly one-third of the parameters of the next best system, while pruning the graphs by 75.2% on average without altering predictions. Our results demonstrate that graph-based representations coupled with counterfactual inference offer both strong predictive accuracy and transparency into the entities driving conspiratorial discourse.