Artificial intelligence and central bank communication: the case of the ECB

We examine whether artificial intelligence (AI) can decipher the European Central Bank's communication. Employing 1769 inter-meeting verbal communication events of the European Central Bank's Governing Council members, we construct an AI-based indicator evaluating whether the communication is leaning towards easing, tightening, or maintaining the monetary policy stance. We find that our AI-based indicator replicates reasonably similar indicators based on human expert judgement but at much higher speed and at much lower costs. Using our AI-based indicator and a number of robustness checks, our regression results show that ECB communication matters for future monetary policy even after controlling for financial market expectations and lagged monetary policy decisions.