Template-Type: ReDIF-Paper 1.0
Author-Name: Byeungchun Kwon
Author-X-Name-First: Byeungchun
Author-X-Name-Last: Kwon
Author-Name: Taejin Park
Author-X-Name-First: Taejin
Author-X-Name-Last: Park
Author-Name: Phurichai Rungcharoenkitkul
Author-X-Name-First: Phurichai
Author-X-Name-Last: Rungcharoenkitkul
Author-Name: Frank Smets
Author-X-Name-First: Frank
Author-X-Name-Last: Smets
Title: Parsing the pulse: decomposing macroeconomic sentiment with LLMs
Abstract: 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.
Creation-Date: 2025-10
File-URL: https://www.bis.org/publ/work1294.pdf
File-Format: Application/pdf
File-Function: Full PDF document
File-URL: https://www.bis.org/publ/work1294.htm
File-Format: text/html
Number: 1294
Keywords: macroeconomic sentiment, growth, inflation, monetary policy, fiscal policy, LLMs, machine learning
Classification-JEL: E30, E44, E60, C55, C82
Handle: RePEc:bis:biswps:1294