We build a new measure of credit and nancial market sentiment using Natural Lan-guage Processing on Twitter data. We nd that the Twitter Financial Sentiment Index(TFSI) correlates highly with corporate bond spreads and other price- and survey-basedmeasures of nancial conditions. We document that overnight Twitter nancial sentimenthelps predict next day stock market returns. Most notably, we show that the index containsinformation that helps forecast changes in the U.S. monetary policy stance: a deteriorationin Twitter nancial sentiment the day ahead of an FOMC statement release predicts thesize of restrictive monetary policy shocks. Finally, we document that sentiment worsens inresponse to an unexpected tightening of monetary policy.