The Wisdom of Twitter Crowds: Predicting Stock Market Reactions to FOMC Meetings via Twitter Feeds

Abstract

1. Pablo D. Azar 1. is a PhD student in the Department of Economics and Laboratory for Financial Engineering in the Sloan School of Management at MIT in Cambridge, MA. (pazar{at}mit.edu) 2. Andrew W. Lo 1. is the Charles E. and Susan T. Harris Professor and the director of the Laboratory for Financial Engineering in the Sloan School of Management at MIT in Cambridge, MA. (alo-admin{at}mit.edu) 1. To order reprints of this article, please contact Dewey Palmieri at dpalmieri{at}iijournals.com or 212-224-3675. With the rise of social media, investors have a new tool for measuring sentiment in real time. However, the nature of these data sources raises serious questions about its quality. Because anyone on social media can participate in a conversation about markets—whether the individual is informed or not—these data may have very little information about future asset prices. In this article, the authors show that this is not the case. They analyze a recurring event that has a high impact on asset prices—Federal Open Market Committee (FOMC) meetings—and exploit a new dataset of tweets referencing the Federal Reserve. The authors show that the content of tweets can be used to predict future returns, even after controlling for common asset pricing factors. To gauge the economic magnitude of these predictions, the authors construct a simple hypothetical trading strategy based on this data. They find that a tweet-based asset allocation strategy outperforms several benchmarks—includi…