Artificial intelligence and central bank communication: the case of the ECB
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11230%2F25%3A10514042" target="_blank" >RIV/00216208:11230/25:10514042 - isvavai.cz</a>
Result on the web
<a href="https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=DOLYMPvYy1" target="_blank" >https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=DOLYMPvYy1</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1080/13504851.2024.2337318" target="_blank" >10.1080/13504851.2024.2337318</a>
Alternative languages
Result language
angličtina
Original language name
Artificial intelligence and central bank communication: the case of the ECB
Original language description
We examine whether artificial intelligence (AI) can decipher the European Central Bank's communication. Employing 1769 inter-meeting verbal communication events of the European Central Bank's Governing Council members, we construct an AI-based indicator evaluating whether the communication is leaning towards easing, tightening, or maintaining the monetary policy stance. We find that our AI-based indicator replicates reasonably similar indicators based on human expert judgement but at much higher speed and at much lower costs. Using our AI-based indicator and a number of robustness checks, our regression results show that ECB communication matters for future monetary policy even after controlling for financial market expectations and lagged monetary policy decisions.
Czech name
—
Czech description
—
Classification
Type
J<sub>imp</sub> - Article in a specialist periodical, which is included in the Web of Science database
CEP classification
—
OECD FORD branch
50201 - Economic Theory
Result continuities
Project
<a href="/en/project/GA20-17044S" target="_blank" >GA20-17044S: Financial Markets Uncertainty: Measurement, Effects and Policy Implications</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2025
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Name of the periodical
Applied Economics Letters
ISSN
1350-4851
e-ISSN
1466-4291
Volume of the periodical
32
Issue of the periodical within the volume
18
Country of publishing house
GB - UNITED KINGDOM
Number of pages
8
Pages from-to
2600-2607
UT code for WoS article
001200488500001
EID of the result in the Scopus database
2-s2.0-85190447249