Researchers have developed a computational framework to extract and quantify environmental actions from unstructured web data, specifically focusing on Jewish congregations in the United States. The study compared three methods for detecting these actions: keyword retrieval with LLM classification, semantic vector retrieval with LLM classification, and direct LLM classification. Direct LLM classification proved most effective, identifying environmental actions at 53% of the congregations studied, offering broader coverage than retrieval-based methods despite potential computational cost reductions from retrieval. AI
IMPACT This framework offers a reproducible method for extracting organizational-level environmental information from unstructured web content, adaptable to various institutions.
RANK_REASON The cluster contains an academic paper detailing a new computational framework and methodology. [lever_c_demoted from research: ic=1 ai=0.7]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
