| Nº Sistema |
000474962 |
| Autor |
 Alonso-Robisco, Andres |
| Autor |
Carbó, José Manuel |
| Título |
Analysis of CBDC narrative by central banks using large language models. [Recurso electrónico] / Andres Alonso-Robisco, Jose Manuel Carbo. |
| Publicado en |
Finance Research Letters [Artículos], v. 58, Part C, December 2023, art. 104643 |
| Nota general |
Artículo de revista |
| Resumen |
One topic that is gaining importance in central bank communication is central bank digital currency (CBDC). To better understand central banks’ stance towards CBDCs, we used different natural language processing techniques on a set of central bank speeches. We found that the sentiment calculated by Large Language Models, and in particular by ChatGPT, is the one that most resembles the sentiment identified by human experts in those same speeches. Our study suggests that LLMs are an effective tool for improving sentiment measurements on specific policy texts, although they are not infallible and may be subject to new risks. [Resumen de autor] [eng] |
| Restricciones |
Acceso electrónico RESTRINGIDO por IP a los usuarios de la Biblioteca del Banco de España |
| Acceso electrónico |
 Acceso al texto completo. |
| Relacionado con |
Documentos de Trabajo / Banco de España; 2321 |
| Clasificación |
G4-Sistemas de pago. |
|
R81-Big data e inteligencia artificial. |
|
E4-Bancos centrales y otras autoridades monetarias. |
| Entidad secundaria |
Banco de España |
