Evolution of topics in central bank speech communication

Abstract

This paper studies the content of central bank speech communication from 1997 through 2020 and asks the following questions: (i) What global topics do central banks talk about? (ii) How do these topics evolve over time? I turn to natural language processing, and more speci cally 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 speci c control variables. I 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 signi cant autoregressive properties not easily explained by nancial control variables.