Combined Use of Topic-Analysis and LLMs on Online Peer-to-Peer Medicaid Discussions to Detect the Impact of HR1 on Individuals Medicaid Experience Across The US

A proof-of-concept combines topic analysis with LLMs to categorize individuals’ Medicaid experiences across multiple US states and over time in response to HR1.

• Why it matters: HR1 is expected to strip Medicaid benefits from 1.8 million people, but state-by-state differences make ongoing monitoring of real-world impacts difficult.
• What they did: The approach uses topic analysis plus LLMs to generate detailed categorizations of Medicaid experiences from online peer-to-peer discussions across states and time.
• The result: It enables continuous, multi-state tracking of how HR1 may affect individuals’ Medicaid experience, supporting human-impact monitoring as administrative requirements take effect in 2027.

AI summary of the abstract · may contain errors · not medical advice · read the paper.