Prattle provides sentiment data from central bank communications. I explored their Central Bank Sentiment Dataset, which contains weekly sentiment data from many central banks around the globe (though I focused on the Federal Reserve Bank). The sentiment data wraps up all publications of the Fed from every week (between about 1998 and 2015) into a score representing the market sentiment of the Fed that week.
I tried to find relationships between sentiment at the Federal Reserve and various macroeconomic-tracking ETFs, such as GLD (gold), TLT (long-term treasury bonds), and DIA (Dow Jones). To mitigate noisy data, I used Kalman-filtered moving averages.
I found particularly strong relationships between Federal Reserve sentiment and SPY and DIA, though their causal relationship is obscured by confounding variables: occasionally the Fed moves first, at other times the ETF moves first. Thus, when taking Fed sentiment data as a signal, it is not easy to know whether you are moving to capture a future trend, or whether you are moving to capture a past trend. This makes it harder to trade on Fed Sentiment, though not at all impossible.
Prattle's data is currently not publicly accessible, so if you want access to it to run your own experiments, or have any questions, please feel free to reach out to [email protected].