Template-Type: ReDIF-Paper 1.0
Author-Name: Angelo M Fasolo
Author-X-Name-First: Angelo M
Author-X-Name-Last: Fasolo
Author-Name: Flávia M Graminho
Author-X-Name-First: Flávia M 
Author-X-Name-Last: Graminho
Author-Name: Saulo B Bastos
Author-X-Name-First: Saulo B
Author-X-Name-Last: Bastos
Title: Seeing the forest for the trees: Using hLDA models to evaluate communication in Banco Central do Brasil
Abstract: Central bank communication is a key tool in managing inflation expectations. This paper proposes a hierarchical Latent Dirichlet Allocation (hLDA) model combined with feature selection techniques to allow an endogenous selection of topic structures associated with documents published by Banco Central do Brasil's Monetary Policy Committee (Copom). These computational linguistic techniques allow building measures of the content and tone of Copom's minutes and statements. The effects of the tone are measured in different dimensions such as inflation, inflation expectations, economic activity, and economic uncertainty. Beyond the impact on the economy, the hLDA model is used to evaluate the coherence between the statements and the minutes of Copom's meetings.
Length: 34 pages
Creation-Date: 2022-06
File-URL: https://www.bis.org/publ/work1021.pdf
File-Format: Application/pdf
File-Function: Full PDF document
File-URL: https://www.bis.org/publ/work1021.htm
File-Format: text/html
Number: 1021
Keywords: communication, monetary policy, latent dirichlet allocation, Brazil, Central Bank
Classification-JEL: E02, E21, E22
Handle: RePEc:bis:biswps:1021