Researchers have developed a method for identifying and extracting conspiratorial actors from German Telegram posts. This approach involves creating annotation guidelines and a corpus of annotated posts, which are then used to train transformer-based models for automatic extraction. The developed model was applied to the Schwurbelarchiv, a large collection of German conspiracy-related Telegram channels, demonstrating the feasibility of large-scale analysis of actor representations in conspiracy narratives. AI
IMPACT Enables large-scale analysis of actor representations in conspiracy narratives, potentially aiding in understanding and combating disinformation.
RANK_REASON The cluster contains an academic paper detailing a new methodology for NLP tasks.
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →