Please use this identifier to cite or link to this item: https://hdl.handle.net/10419/217320 
Year of Publication: 
2018
Citation: 
[Journal:] Central Bank Review (CBR) [ISSN:] 1303-0701 [Volume:] 18 [Issue:] 2 [Publisher:] Elsevier [Place:] Amsterdam [Year:] 2018 [Pages:] 51-60
Publisher: 
Elsevier, Amsterdam
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.
Subjects: 
Central bank
Communication
Reports
Text mining
Cluster analysis
Persistent Identifier of the first edition: 
Creative Commons License: 
cc-by-nc-nd Logo
Document Type: 
Article

Files in This Item:
File
Size





Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.