Researchers have developed an unsupervised framework to identify and analyze competing narratives in political discussions on social media, specifically focusing on German politicians' tweets. This system utilizes a multi-stage pipeline incorporating natural language processing techniques like topic modeling, event detection, and event linking to uncover distinct perspectives and conflicts surrounding political topics. Two case studies on polarizing issues demonstrated the methodology's effectiveness in revealing divergent viewpoints and contributing to the understanding of narrative propagation in the digital public sphere. AI
IMPACT This research offers tools for understanding political discourse dynamics, potentially aiding platforms and policymakers in monitoring online narratives.
RANK_REASON The cluster contains an academic paper detailing a new methodology for analyzing social media discourse. [lever_c_demoted from research: ic=1 ai=0.7]
- arXiv
- event detection
- Event Linking
- German
- Hugging Face
- natural language processing
- social media
- topic modeling
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →