Linking words in economic discourse: implications for macroeconomic forecasts

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 exercise...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autor principal: Aromí, José Daniel
Formato: Artículo
Lenguaje:Inglés
Publicado: Elsevier 2020
Materias:
MACROECONOMIA
ANALISIS DE DATOS
INDICADORES ECONOMICOS
PREVISIONES ECONOMICAS
Acceso en línea:https://repositorio.uca.edu.ar/handle/123456789/10786
https://doi.org/10.1016/j.ijforecast.2019.12.001 0169-2070
Aporte de:
Repositorio Institucional de la Universidad Católica Argentina (UCA) de Universidad Católica Argentina
id I33-R139123456789-10786
record_format dspace
institution Universidad Católica Argentina
institution_str I-33
repository_str R-139
collection Repositorio Institucional de la Universidad Católica Argentina (UCA)
language Inglés
topic MACROECONOMIA
ANALISIS DE DATOS
INDICADORES ECONOMICOS
PREVISIONES ECONOMICAS
spellingShingle MACROECONOMIA
ANALISIS DE DATOS
INDICADORES ECONOMICOS
PREVISIONES ECONOMICAS
Aromí, José Daniel
Linking words in economic discourse: implications for macroeconomic forecasts
topic_facet MACROECONOMIA
ANALISIS DE DATOS
INDICADORES ECONOMICOS
PREVISIONES ECONOMICAS
description 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.
format Artículo
author Aromí, José Daniel
author_facet Aromí, José Daniel
author_sort Aromí, José Daniel
title Linking words in economic discourse: implications for macroeconomic forecasts
title_short Linking words in economic discourse: implications for macroeconomic forecasts
title_full Linking words in economic discourse: implications for macroeconomic forecasts
title_fullStr Linking words in economic discourse: implications for macroeconomic forecasts
title_full_unstemmed Linking words in economic discourse: implications for macroeconomic forecasts
title_sort linking words in economic discourse: implications for macroeconomic forecasts
publisher Elsevier
publishDate 2020
url https://repositorio.uca.edu.ar/handle/123456789/10786
https://doi.org/10.1016/j.ijforecast.2019.12.001 0169-2070
work_keys_str_mv AT aromijosedaniel linkingwordsineconomicdiscourseimplicationsformacroeconomicforecasts
bdutipo_str Repositorios
_version_ 1764820524924403715

Ejemplares similares