Measuring Economic Sentiment from Open-Ended Survey Comments Using Large Language Models


Loading...

Author / Producer

Date

2025-10

Publication Type

Working Paper

ETH Bibliography

yes

Citations

Altmetric

Data

Abstract

This article develops a novel economic sentiment indicator (LLM-ESI) by applying large language models to open-ended responses from Swiss business tendency surveys. Using a BERT-based transformer model, it extracts firmlevel sentiment from free-text survey comments and aggregates it into a highfrequency indicator of macroeconomic conditions. The LLM-ESI closely tracks the business cycle and performs on par with, or better than, traditional benchmarks in nowcasting GDP. These results highlight the potential of large language models and open-ended survey responses to deliver timely and nuanced signals for real-time economic analysis.

Publication status

published

External links

Editor

Book title

Volume

526

Pages / Article No.

Publisher

KOF Swiss Economic Institute, ETH Zurich

Event

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Economic Sentiment; Large Language Model; Business Tendency Surveys; Survey Comments; Textual Analysis; Forecasting

Organisational unit

02525 - KOF Konjunkturforschungsstelle / KOF Swiss Economic Institute check_circle
06331 - KOF FB Konjunkturumfragen / KOF Business Tendency Surveys check_circle

Notes

Funding

Related publications and datasets