Please use this identifier to cite or link to this item: https://repositorio.uca.edu.ar/handle/123456789/10786
Título : Linking words in economic discourse: implications for macroeconomic forecasts
Autor : Aromí, José Daniel 
Palabras clave : MACROECONOMIAANALISIS DE DATOSINDICADORES ECONOMICOSPREVISIONES ECONOMICAS
Fecha de publicación : 2020
Editorial : Elsevier
Cita : Aromí, J. D. Linking words in economic discourse: implications for macroeconomic forecasts [en línea]. International Journal of Forecasting. 2020, 36 (4). Disponible en: https://repositorio.uca.edu.ar/handle/123456789/10786
Proyecto: Estudios de estados subjetivos en contextos microeconómicos 
Resumen : Abstract: This paper develops indicators of unstructured press information by exploiting word vector representations. A model is trained using a corpus covering 90 years of Wall Street Journal content. The information content of the indicators is assessed through business cycle forecast exercises. The vector representations can learn meaningful word associations that are exploited to construct indicators of uncertainty. In-sample and out-of-sample forecast exercises show that the indicators contain valuable information regarding future economic activity. The combination of indices associated with different subjective states (e.g., uncertainty, fear, pessimism) results in further gains in information content. The documented performance is unmatched by previous dictionary-based word counting techniques proposed in the literature.
URI : https://repositorio.uca.edu.ar/handle/123456789/10786
ISSN : 0169-2070
Disciplina: ECONOMIA
DOI: https://doi.org/10.1016/j.ijforecast.2019.12.001 0169-2070
Derechos: Acceso abierto. 24 meses de embargo
Appears in Collections:Artículos

Files in This Item:
File Description SizeFormat Existent users please Login
linking-words-economic-discourse.pdf1,84 MBAdobe PDF???org.dspace.app.webui.jsptag.ItemTag.embargo???    Request a copy
Show full item record

Page view(s)

71
checked on May 14, 2021

Download(s)

44
checked on May 14, 2021

Google ScholarTM

Check


Altmetric


This item is licensed under a Creative Commons License Creative Commons