Monetary Policy in the Media Spotlight: Sentiments, Signals, and Economic Impact

2026-05-14

AI Summary

This study investigates how news media narratives about monetary policy actively shape public expectations and influence macroeconomic outcomes, rather than merely transmitting central bank communications. Leveraging over 50,000 Canadian newspaper articles, the authors construct a novel monetary policy sentiment index by integrating dictionary-based methods, Transformer models, and generative AI—a first in the literature—and embed this measure endogenously within a behavioral New Keynesian framework. Employing Bayesian structural vector autoregression (SVAR) for estimation and counterfactual analysis, the findings reveal that media sentiment significantly affects household inflation and wage expectations, improves out-of-sample forecasting accuracy for GDP and inflation, enters the Taylor rule with statistical significance, and accounts for a non-negligible share of medium-term macroeconomic fluctuations.

Abstract

News media coverage of monetary policy is not a passive transcript of central-bank communication: it filters announcements, macroeconomic news, and editorial choices into narratives that move expectations and policy decisions. We embed media sentiment into a behavioral New-Keynesian model in which the central bank reacts to sentiment and sentiment follows an explicit law of motion. We construct monetary-policy sentiment indicators from more than 50,000 Canadian newspaper articles using dictionary methods, transformer models, and a generative-AI framework. Media sentiment shifts household inflation and wage expectations, improves out-of-sample forecasts of GDP growth and inflation, and loads positively on the Bank of Canada's estimated Taylor rule once treated as endogenous. A Bayesian SVAR identifies anticipated and unanticipated monetary-policy shocks together with a narrative shock; the narrative shock contributes a non-trivial share of medium-horizon macroeconomic variance, and a counterfactual that shuts down the dynamic feedback from media sentiment attenuates the propagation of monetary policy to output and prices. %The results suggest that media narratives are an integral part of monetary-policy transmission, not merely an additional source of information.

Problem

• monetary policy
• media sentiment
• economic expectations
• narrative shock
• policy transmission

Innovation

• media sentiment
• behavioral New-Keynesian model
• generative-AI framework
• Bayesian SVAR
• narrative shock