A1 Refereed original research article in a scientific journal
Exchange rate narratives; 
Authors: Cormun, Vito; Ristolainen, Kim
Publisher: Elsevier
Publication year: 2026
Journal: Journal of International Money and Finance
Article number: 103627
Volume: 167
ISSN: 0261-5606
eISSN: 1873-0639
DOI: https://doi.org/10.1016/j.jimonfin.2026.103627
Publication's open availability at the time of reporting: Open Access
Publication channel's open availability : Partially Open Access publication channel
Web address : https://doi.org/10.1016/j.jimonfin.2026.103627
Self-archived copy’s web address: https://research.utu.fi/converis/portal/detail/Publication/526590934
Self-archived copy's licence: CC BY NC ND
Self-archived copy's version: Publisher`s PDF
We combine Wall Street Journal news, topic modeling, and generative AI to extract economic narratives associated with U.S. dollar fluctuations. Using data since the late 1970s, we isolate six narratives spanning fiscal and monetary policy, financial markets, geopolitical tensions, and technological change. Adding these narratives to standard exchange rate regressions substantially improves the explanatory power of macroeconomic aggregates. The narratives are consistent with shifts in investor attention across exchange rate drivers—a mechanism that generates time-varying loadings on macroeconomic aggregates and helps account for the exchange rate disconnect puzzle.
Keywords:
Big Data, exchange rates, Macroeconomic news, Narrative retrieval, Scapegoat, Textual analysis
Downloadable publication This is an electronic reprint of the original article. |