Template-type: ReDIF-Paper 1.0
Author-Name: Elliot Beck
Author-Name-First: Elliot
Author-Name-Last: Beck
Author-Name: Franziska Eckert
Author-Name-First: Franziska
Author-Name-Last: Eckert
Author-Name: Linus Kühne
Author-Name-First: Linus
Author-Name-Last: Kühne
Author-Name: Helge Liebert
Author-Name-First: Helge
Author-Name-Last: Liebert
Author-Name: Rina Rosenblatt-Wisch
Author-Name-First: Rina
Author-Name-Last: Rosenblatt-Wisch
Author-Person: pro392
Title: Measuring economic outlook in the news
Abstract: We develop a resource-efficient methodology for measuring economic outlook in news text that combines document embeddings with synthetic training data generated by large language models. Applied to 27 million news articles, the resulting indicator significantly improves GDP growth forecast accuracy and captures sentiment shifts weeks before official releases, proving particularly valuable during crises. The indicator outperforms both survey-based benchmarks and traditional dictionary methods and is interpretable, allowing identification of specific drivers of economic sentiment. Our approach addresses key institutional constraints: it performs sentiment classification locally, enabling analyses of proprietary news content without transmission to external services while requiring minimal computational resources compared to direct large language model classification.

Length: 39 pages
Creation-Date: 2026
Contact-Email: forschung@snb.ch
File-URL: https://www.snb.ch/en/publications/research/working-papers/2026/working_paper_2026_04
File-Format: text/html
Number: 2026-04
Classification-JEL: E66, C45, C55
Keywords: Sentiment analysis, Economic outlook, Forecasting, Big data, Large language models, Natural language processing, Neural networks
Handle: RePEc:snb:snbwpa:2026-04