Measurement in the Age of LLMs: An Application to Ideological Scaling

TL;DR

This paper demonstrates how large language models can be used to measure political ideology in text, providing flexible, direct numeric scores that align with traditional methods and capturing subtle ideological nuances.

Contribution

It introduces a novel approach using LLMs to directly elicit ideological scores, enhancing flexibility and applicability in social science measurement tasks.

Findings

LLMs can produce scores closely aligned with established ideological measures.

The method captures subtle and diffuse ideological expressions in text.

Flexible case studies showcase the approach's versatility.

Abstract

Much of social science is centered around terms like ``ideology'' or ``power'', which generally elude precise definition, and whose contextual meanings are trapped in surrounding language. This paper explores the use of large language models (LLMs) to flexibly navigate the conceptual clutter inherent to social scientific measurement tasks. We rely on LLMs' remarkable linguistic fluency to elicit ideological scales of both legislators and text, which accord closely to established methods and our own judgement. A key aspect of our approach is that we elicit such scores directly, instructing the LLM to furnish numeric scores itself. This approach affords a great deal of flexibility, which we showcase through a variety of different case studies. Our results suggest that LLMs can be used to characterize highly subtle and diffuse manifestations of political ideology in text.