CMStatistics 2021: Start Registration
View Submission - CFE
A1682
Title: Evolution of topics in central bank speech communication Authors:  Magnus Hansson - University of Gothenburg (Sweden) [presenting]
Abstract: The content of central bank speech communication from 1997 through 2020 is studied and the following questions are asked: (i) What global topics do central banks talk about? (ii) How do these topics evolve over time? We turn to natural language processing, and more specifically Dynamic Topic Models, to answer these questions. The analysis consists of an aggregate study of nine major central banks and a case study of the Federal Reserve, which allows for region-specific control variables. We show that: (i) Central banks address a broad range of topics. (ii) The topics are well captured by Dynamic Topic Models. (iii) The global topics exhibit strong and significant autoregressive properties not easily explained by financial control variables.