Parsing the Pulse: Decomposing Macroeconomic Sentiment with LLMs
Frank Smets, Deputy Head of the Monetary and Economic Department and Head of Economic Analysis and Statistics at the Bank for International Settlements (BIS), presents his latest research on using Large Language Models (LLMs) to analyze news narratives. The study constructs real-time sentiment indices for growth and inflation, revealing intuitive demand and supply dynamics that complement traditional macroeconomic analysis.
Macroeconomic indicators provide quantitative signals that must be pieced together and interpreted by economists. We propose a reversed approach of parsing press narratives directly using Large Language Models (LLM) to recover growth and inflation sentiment indices. A key advantage of this LLM-based approach is the ability to decompose aggregate sentiment into its drivers, readily enabling an interpretation of macroeconomic dynamics. Our sentiment indices track hard-data counterparts closely, providing an accurate, near real-time picture of the macroeconomy. Their components–demand, supply, and deeper structural forces–are intuitive and consistent with prior model-based studies. Incorporating sentiment indices improves the forecasting performance of simple statistical models, pointing to information unspanned by traditional data.
