Measurement in the Age of LLMs: An Application to Ideological Scaling
This provides a flexible tool for social scientists to quantify subtle political ideology in text, though it is an incremental application of existing LLM capabilities.
The paper tackles the problem of measuring vague social science concepts like ideology by using large language models (LLMs) to directly elicit numeric ideological scores from text, showing that the results align closely with established methods and expert judgment.
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.