Modeling Narrative Archetypes in Conspiratorial Narratives: Insights from Singapore-Based Telegram Groups

2025-12-10

AI Summary

This study challenges the conventional assumption that conspiracy narratives persist solely within isolated echo chambers, investigating their structural characteristics and mechanisms of everyday normalization in Singaporean Telegram groups. Method: We propose a two-stage computational framework: (1) fine-tuned RoBERTa-large for high-accuracy conspiracy message detection (F1 = 0.866); and (2) construction of a signed belief graph, incorporating our novel Signed Belief Graph Neural Network (SiBeGNN) and Sign Disentanglement Loss to decouple ideological stance from linguistic style. Contribution/Results: We identify, for the first time in a local context, seven cross-domain narrative archetypes across 553,000 messages. Clustering achieves cDBI = 8.38—significantly outperforming baselines—and attains 88% inter-expert agreement. Our work establishes a new paradigm for understanding localized radicalization pathways in digital environments.

Technology Category

• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Application Domains: Humanities & Computational Social Science
• Multiagent Systems: Adversarial Agents

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data
• Social Networks and Social Media: Computational social science

Abstract

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.

Problem

• Analyzes how conspiratorial narratives are structured and spread in digital communication ecosystems
• Develops computational framework to identify narrative archetypes within everyday online discussions
• Challenges assumptions about online radicalization by studying conspiratorial discourse in ordinary social interactions

Innovation

• Fine-tuned RoBERTa-large for conspiracy classification
• Built signed belief graph weighted by textual similarity
• Introduced SiBeGNN with Sign Disentanglement Loss for embeddings