Between Hawks and Doves: Measuring Central Bank Communication

41 Pages Posted: 6 Jul 2017

See all articles by Ellen Tobback

Ellen Tobback

University of Antwerp

Stefano Nardelli

European Central Bank (ECB)

David Martens

University of Antwerp

Date Written: July 4, 2017

Abstract

We propose a Hawkish-Dovish (HD) indicator that measures the degree of 'hawkishness' or 'dovishness' of the media's perception of the ECB's tone at each press conference. We compare two methods to calculate the indicator: semantic orientation and Support Vector Machines text classification. We show that the latter method tends to provide more stable and accurate measurements of perception on a labelled test set. Furthermore, we demonstrate the potential use of this indicator with several applications: we perform a correlation analysis with a set of interest rates, use Latent Dirichlet Allocation to detect the dominant topics in the news articles, and estimate a set of Taylor rules. The findings provide decisive evidence in favour of using an advanced text mining classification model to measure the medias perception and the Taylor rule application confirms that communication plays a significant role in enhancing the accuracy when trying to estimate the bank's reaction function.

Keywords: Monetary policy, communication, data mining, quantitative methods

JEL Classification: C02, C63, E52, E58

Suggested Citation

Tobback, Ellen and Nardelli, Stefano and Martens, David, Between Hawks and Doves: Measuring Central Bank Communication (July 4, 2017). ECB Working Paper No. 2085, Available at SSRN: https://ssrn.com/abstract=2997481 or http://dx.doi.org/10.2139/ssrn.2997481

Ellen Tobback

University of Antwerp

Prinsstraat 13
Antwerp, 2000
Belgium

Stefano Nardelli (Contact Author)

European Central Bank (ECB) ( email )

Sonnemannstrasse 22
Frankfurt am Main, 60314
Germany

David Martens

University of Antwerp ( email )

Prinsstraat 13
Antwerp, 2000
Belgium

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
319
Abstract Views
1,267
Rank
173,352
PlumX Metrics