Researchers have developed a pipeline utilizing large language models (LLMs) to extract and categorize claims from extensive social media datasets. This method was applied to Twitter data concerning the 2020 US presidential election and the 2022 FIFA World Cup. The pipeline's effectiveness was rigorously assessed through precision and recall measurements against manually annotated samples, ablation studies, and qualitative error analysis, highlighting its utility for computational social science research. AI
IMPACT This methodology could enhance the analysis of political discourse and polarization on social media platforms.
RANK_REASON The item is a research paper detailing a new methodology for claims extraction. [lever_c_demoted from research: ic=1 ai=1.0]
- 2020 United States presidential election
- 2022 FIFA World Cup
- arXiv
- computational social science
- Sandrine Chausson
- social network analysis
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →