Eleni Kalamara
- 12 January 2022
- ECONOMIC BULLETIN - BOXEconomic Bulletin Issue 8, 2021Details
- Abstract
- This box reviews how the ECB’s communication on the economic outlook has evolved over time and how it compares with that of two other major central banks. Standard metrics reveal that over time the communication on the economic outlook has gradually become clearer, making monetary policy more transparent and effective. The ECB’s communication differs from that of the Bank of England and the Federal Reserve Board, reflecting the differences in their monetary policy strategies. The ECB uses the term “money” more often, while the Bank of England and the Federal Reserve Board communicate the terms “unemployment” and “slack” more frequently. Textual analysis underscores the importance of narratives in communicating quantitative economic forecasts. To build informative narratives, the ECB relies on a wide range of economic models, tools and surveys.
- JEL Code
- E30 : Macroeconomics and Monetary Economics→Prices, Business Fluctuations, and Cycles→General
E50 : Macroeconomics and Monetary Economics→Monetary Policy, Central Banking, and the Supply of Money and Credit→General
- 25 November 2021
- WORKING PAPER SERIES - No. 2616Details
- Abstract
- This paper shows that newspaper articles contain timely economic signals that can materially improve nowcasts of real GDP growth for the euro area. Our text data is drawn from fifteen popular European newspapers, that collectively represent the four largest Euro area economies, and are machine translated into English. Daily sentiment metrics are created from these news articles and we assess their value for nowcasting. By comparing to competitive and rigorous benchmarks, we find that newspaper text is helpful in nowcasting GDP growth especially in the first half of the quarter when other lower-frequency soft indicators are not available. The choice of the sentiment measure matters when tracking economic shocks such as the Great Recession and the Great Lockdown. Non-linear machine learning models can help capture extreme movements in growth, but require sufficient training data in order to be effective so become more useful later in our sample.
- JEL Code
- C43 : Mathematical and Quantitative Methods→Econometric and Statistical Methods: Special Topics→Index Numbers and Aggregation
C45 : Mathematical and Quantitative Methods→Econometric and Statistical Methods: Special Topics→Neural Networks and Related Topics
C55 : Mathematical and Quantitative Methods→Econometric Modeling→Modeling with Large Data Sets?
C82 : Mathematical and Quantitative Methods→Data Collection and Data Estimation Methodology, Computer Programs→Methodology for Collecting, Estimating, and Organizing Macroeconomic Data, Data Access
E37 : Macroeconomics and Monetary Economics→Prices, Business Fluctuations, and Cycles→Forecasting and Simulation: Models and Applications