The value of news for economic developments

Abstract We decompose the textual data in a Norwegian business newspaper into news topics and investigate their role in predicting and explaining economic fluctuations. Separate full- and out-of-sample experiments show that many topics have predictive power for key economic variables, including asset prices. Unexpected innovations to an aggregated news index, derived as a weighted average of the topics with the highest predictive scores, lead to persistent economic fluctuations, and are especially associated with financial markets, credit and borrowing. Unexpected innovations to asset prices, orthogonal to news shocks and labeled as noise, have only temporary positive effects, in line with economic theory.

[1]  N. Bloom Fluctuations in Uncertainty , 2013 .

[2]  David M. Blei,et al.  Supervised Topic Models , 2007, NIPS.

[3]  H. Varian,et al.  Predicting the Present with Google Trends , 2012 .

[4]  Chong Wang,et al.  Reading Tea Leaves: How Humans Interpret Topic Models , 2009, NIPS.

[5]  Clara Vega Stock Price Reaction to Public and Private Information , 2004 .

[6]  M. West,et al.  Bayesian Analysis of Latent Threshold Dynamic Models , 2013 .

[7]  Robert B. Barsky,et al.  News shocks and business cycles , 2011 .

[8]  Pengfei Wang,et al.  Bubbles and Total Factor Productivity , 2012 .

[9]  M. Shapiro,et al.  Forecasting the Recovery from the Great Recession: is this Time Different? , 2013 .

[10]  Robert B. Barsky,et al.  Information, Animal Spirits, and the Meaning of Innovations in Consumer Confidence , 2009 .

[11]  M. West,et al.  Bayesian forecasting and dynamic models , 1989 .

[12]  D. Romer,et al.  The Macroeconomic Effects of Tax Changes: Estimates Based on a New Measure of Fiscal Shocks , 2007 .

[13]  Margaret E. Roberts,et al.  The structural topic model and applied social science , 2013, ICONIP 2013.

[14]  David M. Blei,et al.  Probabilistic topic models , 2012, Commun. ACM.

[15]  Michael I. Jordan,et al.  Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..

[16]  P. Beaudry,et al.  Do Mood Swings Drive Business Cycles and is it Rational? , 2011 .

[17]  Leif Anders Thorsrud,et al.  Boom or Gloom? Examining the Dutch Disease in Two�?Speed Economies , 2014 .

[18]  Julia K. Thomas,et al.  Credit Shocks and Aggregate Fluctuations in an Economy with Production Heterogeneity , 2011, Journal of Political Economy.

[19]  Shimon Kogan,et al.  Which News Moves Stock Prices? A Textual Analysis , 2013 .

[20]  Jean-Paul L’Huillier,et al.  News, Noise, and Fluctuations: An Empirical Exploration , 2009 .

[21]  N. Bloom The Impact of Uncertainty Shocks , 2007 .

[22]  Eric K. Kelley,et al.  The Long-Lasting Momentum in Weekly Returns , 2008 .

[23]  Gregor Heinrich Parameter estimation for text analysis , 2009 .

[24]  S. Davis,et al.  Measuring Economic Policy Uncertainty , 2013 .

[25]  Karel Mertens,et al.  Empirical Evidence on the Aggregate Effects of Anticipated and Unanticipated U.S. Tax Policy Shocks , 2009 .

[26]  V. Ramey,et al.  News Shocks in Open Economies: Evidence from Giant Oil Discoveries , 2015, SSRN Electronic Journal.

[27]  G. Angeletos,et al.  Sentiments ∗ , 2012 .

[28]  P. Beaudry,et al.  News Driven Business Cycles: Insights and Challenges , 2013 .

[29]  M. Shapiro,et al.  Costly Capital Reallocation and the Effects of Government Spending , 1998 .

[30]  G. Lorenzoni A Theory of Demand Shocks , 2006 .

[31]  Sofus A. Macskassy,et al.  More than Words: Quantifying Language to Measure Firms' Fundamentals the Authors Are Grateful for Assiduous Research Assistance from Jie Cao and Shuming Liu. We Appreciate Helpful Comments From , 2007 .

[32]  J. Keynes,et al.  The General Theory of Employment, Interest and Money. , 1936 .

[33]  Marco Lippi,et al.  Noisy News in Business Cycles , 2013 .

[34]  Edoardo M. Airoldi,et al.  Improving and Evaluating Topic Models and Other Models of Text , 2016 .

[35]  P. Beaudry,et al.  Stock Prices, News and Economic Fluctuations , 2003 .

[36]  Paul C. Tetlock Giving Content to Investor Sentiment: The Role of Media in the Stock Market , 2005, The Journal of Finance.

[37]  Michael McMahon,et al.  Transparency and deliberation within the FOMC: a computational linguistics approach , 2014 .