A machine learning framework for automated analysis of central bank communication and media discourse. The case of Narodowy Bank Polski
Bank i Kredyt, 2019, vol. 50, issue 1, 1-20
This paper presents a supervised machine learning framework based on the dictionary and Wordscores models that allows to analyse interactions between the official central bank communication (policy statements) and media discourse (newspaper articles). It was tested on the case of Narodowy Bank Polski in the period 1998−2018, with 70 policy statements accompanying interest rate changes and 21,181 Rzeczpospolita daily articles mentioning the central bank. Using a new concept – correlation of policy lexical sentiment – we found that NBP can successfully affect media discourse when the press discusses topics that fall into the NBP mandate. We also documented that the focus of both RPP statements and press articles changed over time. In the validation procedure we showed that the biggest challenge in applying machine learning to detecting monetary policy inclination in press articles is the existence of many competing policy transmission channels.
Keywords: monetary policy; central bank communication; text mining; Wordscores; Narodowy Bank Polski (search for similar items in EconPapers)
JEL-codes: C8 E5 G14 (search for similar items in EconPapers)
References: Add references at CitEc
Citations: Track citations by RSS feed
Downloads: (external link)
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
Persistent link: https://EconPapers.repec.org/RePEc:nbp:nbpbik:v:50:y:2019:i:1:p:1-20
Access Statistics for this article
More articles in Bank i Kredyt from Narodowy Bank Polski Contact information at EDIRC.
Bibliographic data for series maintained by Michał Wieloch ().