Measuring economic sentiment from open-ended survey comments using large language models
用大语言模型分析瑞士企业调查的开放式评论，构建了一个高频经济情绪指标，能有效追踪商业周期并在GDP预测中表现优于传统基准。
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 firm-level sentiment from free-text survey comments and aggregates it into a high-frequency 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. • Introduces novel LLM-based sentiment index from open-ended survey comments. • Indicator reflects firms’ real-time views and tracks key macroeconomic shocks. • Shows strong cyclical properties and co-moves with business cycle indicators. • Outperforms AR(1) and matches or beats leading indicators in forecasting GDP. • Provides timely, high-frequency tool for policy and economic monitoring.