EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Nowcasting Euro area GDP with news sentiment: A tale of two crises

Julian Ashwin, Eleni Kalamara, Lorena Saiz

Journal of Applied Econometrics · 2024-08 · 39 (5) · 887-905

DOI: 10.1002/jae.3057 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Applied Econometrics, online erschienen am 09.05.2024. Verfasst von Julian Ashwin und 2 weiteren Autor:innen. Die Arbeit wurde bisher 22-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper shows that newspaper articles contain signals that can materially improve real‐time nowcasts of real GDP growth for the Euro area. Using articles from 15 popular European newspapers, which are machine translated into English, we create sentiment metrics that update daily and assess their value for nowcasting, comparing with competitive and rigorous benchmarks. We find that newspaper text is especially helpful early in the quarter before other indicators are available. We also find that general‐purpose sentiment measures perform better than more economics‐focused ones in response to unanticipated events and nonlinear supervised models can help capture extreme movements in growth but require sufficient training data to be effective.

Zitieren

APA

Ashwin, J., Kalamara, E., & Saiz, L. (2024). Nowcasting Euro area GDP with news sentiment: A tale of two crises. Journal of Applied Econometrics, 39(5), 887-905. https://doi.org/10.1002/jae.3057

Vancouver

Ashwin J, Kalamara E, Saiz L. Nowcasting Euro area GDP with news sentiment: A tale of two crises. Journal of Applied Econometrics. 2024;39(5):887-905. doi:10.1002/jae.3057

BibTeX
@article{Ashwin2024,
  author = {Ashwin, Julian and Kalamara, Eleni and Saiz, Lorena},
  title = {Nowcasting Euro area GDP with news sentiment: A tale of two crises},
  journal = {Journal of Applied Econometrics},
  year = {2024},
  volume = {39},
  number = {5},
  pages = {887--905},
  doi = {10.1002/jae.3057}
}
Kostenlos starten →