Forecasting in ation with twitter

We use Twitter content to generate an indicator of the level of attention allocated to inflation in public discussions. The analysis corresponds to Argentina for the period 2012-2019. Estimated forecasting models show that the indicator provides valuable information regarding future levels of inflat...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Aromi, Daniel, Llada, Martín
Formato: Artículo publishedVersion
Lenguaje:Español
Publicado: Instituto Interdisciplinario de Economía Política (IIEP UBA-CONICET) 2023
Materias:
Acceso en línea:https://ojs.economicas.uba.ar/DT-IIEP/article/view/2620
https://repositoriouba.sisbi.uba.ar/gsdl/cgi-bin/library.cgi?a=d&c=dociiep&d=2620_oai
Aporte de:
Descripción
Sumario:We use Twitter content to generate an indicator of the level of attention allocated to inflation in public discussions. The analysis corresponds to Argentina for the period 2012-2019. Estimated forecasting models show that the indicator provides valuable information regarding future levels of inflation. Out-of-sample exercises confirm that social media content allows for gains in forecast accuracy. Beyond point forecasts, the index provides valuable information regarding inflation uncertainty, that is, the size of forecast errors confidence intervals. The proposed indicator compares favorably with other indicators such as media content, media tweets, google search intensity and consumer surveys.