An LLM-filtered pipeline with UMAP and HDBSCAN clustering identifies 41 manipulative narrative clusters from 1.2 million social media posts.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
LLM-based Detection of Manipulative Political Narratives
An LLM-filtered pipeline with UMAP and HDBSCAN clustering identifies 41 manipulative narrative clusters from 1.2 million social media posts.