Reuters Sentiment and Stock Returns
2014; Routledge; Volume: 15; Issue: 4 Linguagem: Inglês
10.1080/15427560.2014.967852
ISSN1542-7579
Autores Tópico(s)Auditing, Earnings Management, Governance
ResumoAbstractSentiment from more than 3.6 million Reuters news articles is tested in a vector autoregression model framework on its ability to forecast returns of the Dow Jones Industrial Average stock index. We show that Reuters sentiment can explain and predict changes in stock returns better than macroeconomic factors. We further find that negative Reuters sentiment has more predictive power than positive Reuters sentiment. Trading strategies with Reuters sentiment achieve significant outperformance with high success rates as well as high Sharpe ratios.Keywords: Reuters sentimentStock returnsOut-of-sample forecastsVector autoregression model ACKNOWLEDGMENTSThanks to Thomson Reuters for the sentiment dataset. I am grateful to Didier Sornette and Jan-Egbert Sturm for helpful comments and suggestions. Thanks also to discussants and participants of the internal research seminar at MAN Investments, the World Finance Conference, and the European Financial Management Conference for their feedback and suggestions. I thank Edward Fridael for his technology support.Notes1. See also Cao and Wei [2005] Cao, M. and J. Wei. “Stock Market Returns: A Note on Temperature Anomaly.” Journal of Banking and Finance, 29, (2005), pp. 1559–1573.[Crossref], [Web of Science ®] , [Google Scholar], Edmans et al [2007] Edmans, A., D. Garcia and O. Norli. “Sports Sentiment and Stock Returns.” Journal of Finance, 62, (2007), pp. 1967–1998.[Crossref], [Web of Science ®] , [Google Scholar], Hirshleifer [2001] Hirshleifer, D. “Investor Psychology and Asset Pricing.” Journal of Finance, 91, (2001), pp. 342–346. [Google Scholar], Hirshleifer and Shumway [2003] Hirshleifer, D. and T. Shumway. “Good Day Sunshine: Stock Returns and the Weather.” Journal of Finance, 58, (2003), pp. 1009–1032.[Crossref], [Web of Science ®] , [Google Scholar], Kamstra et al. [2003] Kamstra, M., L. Kramer and M. Levi. “Winter Blues: A SAD Stock Market Cycle.” American Economic Review, 93, (2003), pp. 324–343.[Crossref], [Web of Science ®] , [Google Scholar], Maier [2005] Maier, S. R. “Accuracy Matters: A Cross-Market Assessment of Newspaper Error and Credibility.” Journalism & Mass Communication Quarterly, 82, (2005), pp. 533–551.[Crossref], [Web of Science ®] , [Google Scholar], Mullainathan and Shleifer [2005] Mullainathan, S. and A. Shleifer. “The Market for News.” American Economic Review, 95, (2005), pp. 1031–1053.[Crossref], [Web of Science ®] , [Google Scholar], and Yuan et al. [2006] Yuan, K. L. Zheng and Q. Zhu. “Are Investors Moonstruck? Lunar Phases and Stock Returns.” Journal of Empirical Finance, 13, (2006), pp. 1–23.[Crossref] , [Google Scholar], among others.2. Note: low pessimism is not equal to optimism, as Tetlock [2007] Tetlock, P. C. “Giving Content to Investor Sentiment: The Role of Media in the Stock Market.” Journal of Finance, 62, (2007), pp. 1139–1168.[Crossref], [Web of Science ®] , [Google Scholar] only considers negative words—a measure only for pessimism—in his analysis.3. See The General Inquirer Home Page, available at http://www.wjh.harvard.edu/∼inquirer/.4. See Thomson Reuters News Analytics, http://thomsonreuters.com/products_services/financial/financial_products/quantitative_research_trading/news_analytics.5. The topics range from financial market to economic and political news, categorized into topic codes. See Reuters Codes—a quick guide, available at https://customers.reuters.com/training/trainingCRMdata/promo_content/ReutersCodes.pdf.6. We filter for “U” in the product code section, and for “DIV, MRG, RES, RESF, RCH, STX” in the topic code section. These codes mean that we filter for news related to dividends, ownership changes, broker research, corporate results, results forecasts and stock markets for North American companies.7. See www.masterdatacsv.com.8. See Global Business Cycles Indicators for more detailed information at http://www.conference-board.org/economics/bci.9. See also Chan [2003] Chan, W. S. “Stock Price Reaction to News and No-News: Drift and Reversal After Headlines.” Journal of Financial Economics, 70, (2003), pp. 223–260.[Crossref], [Web of Science ®] , [Google Scholar] for evidence of a postnews drift.10. See Appendix A.1 for a more detailed description of the forecasting errors according in Lütkepohl [1991] Lütkepohl, H. Introduction to Multiple Time Series Analysis. Berlin: Springer Verlag, 1991.[Crossref] , [Google Scholar].11. See Appendix A.2 for the derivation of the Sharpe Ratio according to Sharpe [1994] Sharpe, W. F. “The Sharpe Ratio.” Journal of Portfolio Management, 21, (1994), pp. 49–58.[Crossref], [Web of Science ®] , [Google Scholar].12. Success Rate = number of correctly forecast trading direction (i.e., up or down) months divided by number of total forecast months.
Referência(s)