Monetary Policy and Financial Markets: Evidence from Twitter Traffic

Abstract

The monetary policy announcements of major central banks trigger significant discussions on social media. In this paper, we use machine learning tools to identify Twitter messages related to monetary policy within a narrow timeframe surrounding the release of policy decisions by three major central banks: the European Central Bank, the Federal Reserve, and the Bank of England. We construct a measure of similarity between tweets discussing monetary policy and the content of policy announcements. This measure serves to assess both the ex-ante predictability and the ex-post credibility of the announcements. We provide evidence that large differences in similarity are associated with increased stock market and sovereign yield volatility, particularly around European Central Bank press conferences. Additionally, our findings show a strong link between changes in similarity and asset price returns for the European Central Bank, but less so for the Federal Reserve or the Bank of England.