Identifying Social Class and Networks from US Legislative Biographies using LLMs

This project explores the application of Large Language Models (LLMs) to unstructured biographical texts found in official US legislative journals. The primary objective is to evaluate the feasibility of using LLMs to parse narrative text and identify specific variables related to social class (such as education and occupation) and network connections (such as shared organizational memberships). The study aims to develop a workflow for converting these biographical entries into structured data, allowing for a preliminary analysis of the socioeconomic composition and relational ties within the legislature.