# Belief Is All You Need: Modeling Narrative Archetypes in Conspiratorial Discourse

arXiv: https://arxiv.org/abs/2512.10105 · HTML: https://mlsanity.com/paper/2512.10105/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 47 references that are in the map.
- First posted on arXiv 10 Dec 2025.

## Builds on (most cited first, 12 of 12)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [Debunking in a World of Tribes](https://mlsanity.com/paper/1510.04267/) (2015)
- [Signed Graph Convolutional Network](https://mlsanity.com/paper/1808.06354/) (2018)
- [Agentic AI framework for End-to-End Medical Data Inference](https://mlsanity.com/paper/2507.18115/) (2025)
- [Signed Graph Representation Learning: A Survey](https://mlsanity.com/paper/2402.15980/) (2024)
- [Classifying Conspiratorial Narratives At Scale: False Alarms and Erroneous Connections](https://mlsanity.com/paper/2404.00141/) (2024)
- [Partisan US News Media Representations of Syrian Refugees](https://mlsanity.com/paper/2206.09024/) (2022)
- [User Archetypes and Information Dynamics on Telegram: COVID-19 and Climate Change Discourse in Singapore](https://mlsanity.com/paper/2406.06717/) (2024)
- [TeleScope: A Longitudinal Dataset for Investigating Online Discourse and Information Interaction on Telegram](https://mlsanity.com/paper/2504.19536/) (2025)

## Abstract (arXiv)

Conspiratorial discourse is increasingly embedded within digital communication ecosystems, yet its structure and spread remain difficult to study. This work analyzes conspiratorial narratives in Singapore-based Telegram groups, showing that such content is woven into everyday discussions rather than confined to isolated echo chambers. We propose a two-stage computational framework. First, we fine-tune RoBERTa-large to classify messages as conspiratorial or not, achieving an F1-score of 0.866 on 2,000 expert-labeled messages. Second, we build a signed belief graph in which nodes represent messages and edge signs reflect alignment in belief labels, weighted by textual similarity. We introduce a Signed Belief Graph Neural Network (SiBeGNN) that uses a Sign Disentanglement Loss to learn embeddings that separate ideological alignment from stylistic features. Using hierarchical clustering on these embeddings, we identify seven narrative archetypes across 553,648 messages: legal topics, medical concerns, media discussions, finance, contradictions in authority, group moderation, and general chat. SiBeGNN yields stronger clustering quality (cDBI = 8.38) than baseline methods (13.60 to 67.27), supported by 88 percent inter-rater agreement in expert evaluations. Our analysis shows that conspiratorial messages appear not only in clusters focused on skepticism or distrust, but also within routine discussions of finance, law, and everyday matters. These findings challenge common assumptions about online radicalization by demonstrating that conspiratorial discourse operates within ordinary social interaction. The proposed framework advances computational methods for belief-driven discourse analysis and offers applications for stance detection, political communication studies, and content moderation policy.