Monetary policy press releases: an international comparison

BIS Working Papers  |  No 1023  | 
14 June 2022
PDF full text
 |  42 pages

This paper was produced as part of the Final Conference of the BIS-CCA Research Network on "Monetary policy frameworks and communication (2019-2022)".



Central banks around the world distribute press releases detailing their monetary policy decisions. Central banks also include in those publications rationalizations for the policy choices and information about the central bank's economic projections. These documents may help guide the evolution of the policy rates by examining the discussions about future economic conditions.


We examine the central bank press releases of inflation-targeting countries with a relatively long set of document releases. We conduct Latent Dirichlet Allocation to build custom dictionaries for each country, which allows us to account for the way central banks use certain terms and descriptions for their policy decisions and projections. We use an algorithmic Sentiment Analysis with the custom dictionary to calculate sentiment indices. We examine how these sentiment scores help predict future policy rate movements and evaluate how these indices co-move over time. Lastly, we evaluate the average impact of the sentiment index of the Federal Reserve press releases on the projections of sentiment scores of future press releases of other central banks.


For a significant majority of inflation-targeting countries, the sentiment indices help predict the monetary policy changes in the short and medium term. Central banks can use the sentiment index to further refine their monetary policy press releases and more effectively convey information about their policy expectations. Moreover, many of the sentiment indices we evaluated have strong co-movements, especially during turbulent economic episodes, such as the Great Financial Crisis. This reflects the similarity in what central banks focus on as they make decisions about optimal monetary policy.


Around the world, several countries have adopted inflation targeting as their monetary policy framework. These institutions set their target interest rates in monetary policy meetings. These decisions are then circulated through press releases that explain the policy rationale. The information contained in the press releases includes current policies, economic outlook, and signals about likely future policies. In this paper, using linguistic methods, such as Latent Dirichlet Allocation (LDA) and semi-automated content analysis, we examine the information contained in the monetary press releases of inflation targeting countries. In addition, we build a custom dictionary for analyzing monetary policy press releases. Using Semi-automated Content Analysis, we then develop a measure, which we refer to as the Sentiment Score index, that quantifies the policy tilt implied in the information provided in the press releases. We find that for a significant majority of the in flation targeting countries, the index provides additional information that helps predict monetary policy rate movements.

JEL classification: E44, E52, E58.

Keywords: central bank, financial market, monetary policy, communication.