# From Repetition to Recognition: Inductive Discovery of Disinformation Narratives

arXiv: https://arxiv.org/abs/2609.11128 · HTML: https://mlsanity.com/paper/2609.11128/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 88 references that are in the map.
- First posted on arXiv 10 Sep 2026.

## Builds on (most cited first, 10 of 10)

- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [BERTopic: Neural topic modeling with a class-based TF-IDF procedure](https://mlsanity.com/paper/2203.05794/) (2022)
- [From Louvain to Leiden: guaranteeing well-connected communities](https://mlsanity.com/paper/1810.08473/) (2018)
- [NodeRAG: Structuring Graph-based RAG with Heterogeneous Nodes](https://mlsanity.com/paper/2504.11544/) (2025)
- [An automated pipeline for the discovery of conspiracy and conspiracy theory narrative frameworks: Bridgegate, Pizzagate and storytelling on the web](https://mlsanity.com/paper/2008.09961/) (2020)
- [Specious Sites: Tracking the Spread and Sway of Spurious News Stories at Scale](https://mlsanity.com/paper/2308.02068/) (2023)
- [UKElectionNarratives: A Dataset of Misleading Narratives Surrounding Recent UK General Elections](https://mlsanity.com/paper/2505.05459/) (2025)
- [Narrative Media Framing in Political Discourse](https://mlsanity.com/paper/2506.00737/) (2025)
- [Cross-Platform Narrative Prediction: Leveraging Platform-Invariant Discourse Networks](https://mlsanity.com/paper/2510.09464/) (2025)
- [Retrieving Climate Change Disinformation by Narrative](https://mlsanity.com/paper/2603.22015/) (2026)

## Abstract (arXiv)

In disinformation datasets, narratives are often understood as recurring interpretive patterns that group texts under narrative labels. Recent work formalized narrative mining as inductively inferring narrative labels from corpora, but its evaluation stays tied to predefined taxonomies, a closed-world setting that cannot capture narratives absent from the reference labels. We introduce a three-tier evaluation framework for unsupervised narrative label generation: recovery (against a corpus's own taxonomy), mining (against external label sets), and discovery (without predefined labels). Applying it, we compare clustering-based and graph-community-based pipelines across seven disinformation datasets, with human validation of discovery on two. The two families are complementary under automated metrics, but in a corpus with two prominent topics, clustering can reduce one topic to 2% of generated labels while graph-based pipelines stay balanced. Discovery validation also reveals many singletons (narrative labels derived from single claims, 30-62% of graph outputs), which clustering cannot produce. Annotators confirm many as recognizable disinformation narratives, suggesting that in open-world discovery the repetition assumed by narrative mining may be recognized outside the corpus, not within it. We release human-validated narrative candidate labels for the Climate Obstruction and PolyNarrative datasets to support taxonomy development and dataset extension.