5 Monetary Policy on Twitter and its Effect on Asset Prices: Evidence from Computational Text
5.6 Conclusions
The expectations about future monetary policy matter for asset prices. The process in which expectations are formed, however, is opaque. A key contribution to expectations formation is the public debate about future monetary policy among households and investors. This paper dissects the debate about monetary policy for a period with large swings in policy expectations - the “taper tantrum” episode in 2013. Based on a large dataset containing all Twitter messages on the Fed’s unwinding of asset purchases (“tapering”) we use computational linguistic methods (LDA) to slice the debate into different topics. The frequencies of selected topics are then modeled in a VAR framework. We show that shocks to selected topic frequencies have significant effects on U.S. bond yields, exchange rates and stock prices.
The results are robust to the specification of the VAR model and suggest that the discourse about policy in social media matters for asset prices. With the help of social media we can shed light on the black box of expectations formation, that is, how people share and comment on information and how an aggregate market view evolves. For applications for which expectations play an important role, such as monetary policy, asset pricing and central bank communication, social media offers interesting opportunities. In particular, questions
142
5.6 Conclusions
related to central bank communication and expectations management, respectively, could be addressed by using high-frequency social media data.
In future research the cross-section or network dimension of the data can be used. The present paper employs daily aggregates of the Twitter exchange. It might also be fruitful to exploit the high-frequency flow of information in the network of Twitter users and the resulting formation of expectations.
5 Monetary Policy on Twitter and its Effect on Asset Prices
Bibliography
Adrian, T., R. K. Crump, and E. Moench (2013). “Pricing the term structure with linear regressions”. In:Journal of Financial Economics 110.1, pp. 110–138.
Aizenman, J., M. Binici, and M. M. Hutchison (2016). “The Transmission of Federal Reserve Tapering News to Emerging Financial Markets”. In:International Journal of Central Banking 12.2, pp. 317–356.
Bauer, M. D. and G. D. Rudebusch (2014). “The Signaling Channel for Federal Reserve Bond Purchases”. In: International Journal of Central Banking 10.3, pp. 233–289.
Bholat, D., S. Hans, P. Santos, and C. Schonhardt-Bailey (2015).Text mining for central banks. Handbooks 33. Centre for Central Banking Studies, Bank of England.
Blei, D. M. and J. D. Lafferty (2007). “A correlated topic model of Science”. In:Annals of Applied Statistics 1.1, pp. 17–35.
Blei, D. M., A. Y. Ng, and M. I. Jordan (2003). “Latent dirichlet allocation”. In:Journal of machine Learning Research 3, pp. 993–1022.
Blinder, A. S., M. Ehrmann, M. Fratzscher, J. D. Haan, and D.-J. Jansen (2008). “Central Bank Communication and Monetary Policy: A Survey of Theory and Evidence”. In:Journal of Economic Literature 46.4, pp. 910–45.
Deerwester, S. C., S. T. Dumais, T. K. Landauer, G. W. Furnas, and R. A. Harshman (1990).
“Indexing by latent semantic analysis”. In:Journal of the American Society for Information Science 41.6, pp. 391–407.
Eichengreen, B. and P. Gupta (2015). “Tapering talk: The impact of expectations of reduced Federal Reserve security purchases on emerging markets”. In:Emerging Markets Review 25.C, pp. 1–15.
Goldsmith-Pinkham, P., B. Hirtle, and D. O. Lucca (2016). Parsing the content of bank supervision. Staff Reports 770. Federal Reserve Bank of New York.
144
Bibliography
Griffiths, T. L. and M. Steyvers (2004). “Finding scientific topics”. In: Proceedings of the National Academy of Sciences 101.suppl 1, pp. 5228–5235.
Grün, B. and K. Hornik (2011). “topicmodels: An R Package for Fitting Topic Models”. In:
Journal of Statistical Software 40.13, pp. 1–30.
Hansen, S. and M. McMahon (2016). “Shocking language: Understanding the macroeco-nomic effects of central bank communication”. In: Journal of International Economics 99, Supplement 1. 38th Annual NBER International Seminar on Macroeconomics, S114–S133.
Hansen, S., M. McMahon, and A. Prat (2014). Transparency and Deliberation within the FOMC: A Computational Linguistics Approach. CEP Discussion Papers dp1276. Centre for Economic Performance.
Hendry, S. (2012).Central Bank Communication or the Media’s Interpretation: What Moves Markets? Staff Working Papers 12-9. Bank of Canada.
Hendry, S. and A. Madeley (2010). Text Mining and the Information Content of Bank of Canada Communications. Staff Working Papers 10-31. Bank of Canada.
Hofmann, T. (1999). “Probabilistic latent semantic indexing”. In: Proceedings of the 22nd annual international ACM SIGIR conference on Research and development in information retrieval. ACM, pp. 50–57.
Larsen, V. H. and L. A. Thorsrud (2015). The Value of News. Working Papers 0034. Centre for Applied Macro- and Petroleum economics (CAMP), BI Norwegian Business School.
Loughran, T. and B. McDonald (2016). “Textual Analysis in Accounting and Finance: A Survey”. In: Journal of Accounting Research 54.4, pp. 1187–1230.
Lucca, D. O. and F. Trebbi (2009).Measuring Central Bank Communication: An Automated Approach with Application to FOMC Statements. NBER Working Papers 15367. National Bureau of Economic Research.
Lüdering, J. and P. Winker (2016). “Forward or backward looking? The economic discourse and the observed reality”. In: Jahrbücher für Nationalökonomie und Statistik 236.4, pp. 483–
516.
5 Monetary Policy on Twitter and its Effect on Asset Prices
Meinusch, A. and P. Tillmann (2016).Quantitative Easing and tapering uncertainty: evidence from Twitter. unpublished. Giessen University.
Mishra, P., K. Moriyama, P. M. P. N’Diaye, and L. Nguyen (2014). Impact of Fed Taper-ing Announcements on EmergTaper-ing Markets. IMF WorkTaper-ing Papers 14/109. International Monetary Fund.
Schonhardt-Bailey, C. (2013).Deliberating Monetary Policy. MIT Press, Cambridge.
Tetlock, P. C. (2007). “Giving Content to Investor Sentiment: The Role of Media in the Stock Market”. In:Journal of Finance 62.3, pp. 1139–1168.
Thornton, D. L. (2012). Evidence on the portfolio balance channel of quantitative easing.
Working Papers 2012-015A. Federal Reserve Bank of St. Louis.
Wang, X. and A. McCallum (2006). “Topics over Time: A non-Markov Continuous-time Model of Topical Trends”. In: Proceedings of the 12th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. KDD ’06, pp. 424–433.
Wu, T. (2014).Unconventional Monetary Policy and Long-Term Interest Rates. IMF Working Papers 14/189. International Monetary Fund.
146