Narratives to Numbers: Large Language Models and Economic Policy Uncertainty

TL;DR

This paper demonstrates that large language models significantly improve the measurement of economic policy uncertainty from news texts, outperforming traditional methods and enabling historical and cross-country analysis.

Contribution

It introduces a novel approach using LLMs for estimating economic uncertainty indices, surpassing dictionary-based methods and extending to multilingual and historical data.

Findings

LLMs outperform dictionary rules in tracking human assessments

Constructed a new 19th-century U.S. economic uncertainty index

Extended indices to multilingual and historical news sources

Abstract

This study evaluates large language models as estimable classifiers and clarifies how modeling choices shape downstream measurement error. Revisiting the Economic Policy Uncertainty index, we show that contemporary classifiers substantially outperform dictionary rules, better track human audit assessments, and extend naturally to noisy historical and multilingual news. We use these tools to construct a new nineteenth-century U.S. index from more than 360 million newspaper articles and exploratory cross-country indices with a single multilingual model. Taken together, our results show that LLMs can systematically improve text-derived measures and should be integrated as explicit measurement tools in empirical economics.