A text mining application on monthly price developments reports

Hatice Burcu Eskici and Necmettin Alpay Koçak

Central Bank Review, 2018, vol. 18, issue 2, 51-60

Abstract: Text mining analysis provides big opportunities for economic research. Underlying natural language processing techniques allow us to read the monthly price developments reports (MPDR) of the Central Bank of the Republic of Turkey (CBRT) and to analyse the words, to explore topics and clusters inside. Previous literature on CBRT documents has focused on making word clouds, measuring the sentiments and therefore it is limited with text documents. This study sets out to close this gap and extends the text mining analysis to measure the statistical consistency of the MPRDs with the annual consumer price index (CPI) inflation figures for Turkey. In this study, we showed that MPDRs contain intensifying references to core-groups/sectors in evaluation of inflation as well as they are interested in the tendency of inflation rather than its level. We also showed that how the clusters of MPDRs are significantly consistent with the annual CPI inflation figures from statistical point of view.

Keywords: Central bank; Communication; Reports; Text mining; Cluster analysis (search for similar items in EconPapers)
Date: 2018
References: Add references at CitEc
Citations: View citations in EconPapers (3)

Downloads: (external link)
https://www.sciencedirect.com/journal/central-bank-review/vol/18/issue/2 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:tcb:cebare:v:18:y:2018:i:2:p:51-60

Access Statistics for this article

More articles in Central Bank Review from Research and Monetary Policy Department, Central Bank of the Republic of Turkey Contact information at EDIRC.
Bibliographic data for series maintained by () and () and () and ().