Skip to main content

Text Analysis System for Measuring the Influence of News Articles on Intraday Price Changes in Financial Markets

  • Conference paper
  • First Online:
Agent and Multi-Agent Systems: Technology and Applications

Part of the book series: Smart Innovation, Systems and Technologies ((SIST,volume 58))

Abstract

This study constructs a text analysis system for analyzing financial markets. This system enables us to investigate the influence of news article on intraday price changes. In this study, we examine the automobile companies in Japan to analyze the relationship between news articles and stock price reactions. As a result of empirical analyses, we confirmed that stock prices reflect news information in a timely manner. These results are suggestive from both academic and practical view points. More detailed analyses are planned for the future.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 84.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 109.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info
Hardcover Book
USD 109.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    In parallel with the rapid progress of computational technologies, various kinds of methods proposed in computer science—such as machine learning, agent-based modeling and network analysis—have been applied to financial research [1, 15, 18, 21, 22].

  2. 2.

    In this study, we selected Support Vector Regression with the linear kernel as a supervised learning. But our proposed system can work with other kinds of supervised learning.

  3. 3.

    In procedures 1 and 2, we analyze all Japanese news articles in relation to the Japanese stock market during the sample periods.

  4. 4.

    Although, we don’t employ a deep learning model in this study, in another article [10], we employ a recursive neural network model to analyze the relationship between news and stock indices. Detailed analysis using both a recursive neural network model and intraday price changes is one of our future plans.

  5. 5.

    These companies are ranked in the top three companies in the automobile sector in Japan.

  6. 6.

    The number of each category crucially depends on the classification procedure (Figs. 3, 5). A detailed analysis is planned for the future.

  7. 7.

    \(\mathrm{Time}=0\) in x-axis shows the point when news articles are released to investors.

References

  1. Bishop, C.M.: Pattern Recognition and Machine Learning. Springer (2006)

    Google Scholar 

  2. Black, F., Scholes, M.: The pricing of options and corporate liabilities. J. Polit. Econ. 81(3), 637–654 (1973)

    Article  MATH  Google Scholar 

  3. Brealey, R.A.: Principles of Corporate Finance 8th Edition. Irwin/McGraw-Hill (2006)

    Google Scholar 

  4. Campbell, J.Y., Lo, A.W., MacKinlay, A.C. : The Econometrics of Financial Markets. Princeton University Press (1997)

    Google Scholar 

  5. Engelberg, J., Reed, A.V., Ringgenber, M.C.: How are shorts informed? and information processing. J. Fin. Econ. 105(2), 260–278 (2012)

    Article  Google Scholar 

  6. Fama, E.: Efficient capital markets: a review of theory and empirical work. J. Fin. 25(2), 383–417 (1970)

    Article  Google Scholar 

  7. Fama, E.F., French, K.R.: Common risk factors in the returns on stock and bonds. J. Fin. Econ. 33(1), 3–56 (1993)

    Article  MATH  Google Scholar 

  8. Garcia, D.: Sentiment during recessions. J. Fin. 68(3), 1267–1300 (2013)

    Article  Google Scholar 

  9. Goshima, K., Takahashi, H., Terano, T.: Estimating financial words’ negative-positive from stock prices. In: The 21st International Conference Computing in Economics and Finance (2015)

    Google Scholar 

  10. Goshima, K., Takahashi, H.: Quantifying news tone to analyze Tokyo stock exchange with recursive neural networks. Secur. Anal. J. 54(3), 76–86 (2016)

    Google Scholar 

  11. Healy, A.D., Lo, A.W.: Managing real-time risks and returns: the thomson reuters newsscope event indices. In: Mitra, G., Mitra, L. (eds.) The Handbook of New Analytics in Finance. Wiley, West Sussex (2011)

    Google Scholar 

  12. Henry, A.: Are investors influenced by how earnings press releases are written? J. Bus. Commun. 45(4), 363–407 (2008)

    Article  Google Scholar 

  13. Ingersoll, J.E.: Theory of Financial Decision Making. Rowman & Littlefield (1987)

    Google Scholar 

  14. Kearney, C., Liu, S.: Textual sentiment in finance : a survey of methods and models. Int. Rev. Fin. Anal. 33, 171–185 (2014)

    Article  Google Scholar 

  15. Kikuchi, T., Takahashi, H., Terano, T.: The propagation of bankruptcies of financial institutions? an agent model of financing behavior and asset price fluctuations. In: The 9th International Workshop on Agent-based Approach in Economic and Social Complex Systems (2015)

    Google Scholar 

  16. Loughran, T., McDonald, B.: When Is a liability not a liability? textual analysis, dictionaries, and 10-Ks. J. Fin. 66(1), 35–65 (2011)

    Article  Google Scholar 

  17. Luenberger, D.G.: Investment Science. Oxford University Press, Oxford (2000)

    Google Scholar 

  18. May, R.M. Arinaminpathy, N.: Systemic risk: the dynamics of model banking system. J. R. Soc. Interface 7(46), 823–838 (2010)

    Google Scholar 

  19. O’Brien, P.C.: Analysts’ forecasts as earnings expectations. J. Acc. Econ. 10(1), 53–83 (1988)

    Article  Google Scholar 

  20. Sharpe, W.F.: Capital asset prices: a theory of market equilibrium under condition of risk. J. Fin. 19(3), 425–442 (1964)

    Google Scholar 

  21. Takahashi, H., Terano, T.: Agent-based approach to investors’ behavior and asset price fluctuation in financial markets. J. Artif. Soc. Soc. Simul. 6(3) (2003)

    Google Scholar 

  22. Takahashi, H.: An analysis of the influence of dispersion of valuations on financial markets through agent-based modeling. Int. J. Inf. Technol. Decis. Making 11, 143–166 (2012)

    Article  Google Scholar 

  23. Tetlock, P.C.: Giving content to investor sentiment: the role of media in the stock market. J. Fin. 62(3), 1139–1168 (2007)

    Article  Google Scholar 

  24. Tetlock, P.C., Saar-Tsechansky, M., Macskassy, S.: More than words: quantifying language to measure firms’s fundamentals. J. Fin. 63(3), 1437–1467 (2008)

    Article  Google Scholar 

Download references

Acknowledgments

This research was supported by a grant-in-aid from the Telecommunications Advancement Foundation.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Keiichi Goshima .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2016 Springer International Publishing Switzerland

About this paper

Cite this paper

Goshima, K., Takahashi, H. (2016). Text Analysis System for Measuring the Influence of News Articles on Intraday Price Changes in Financial Markets. In: Jezic, G., Chen-Burger, YH., Howlett, R., Jain, L. (eds) Agent and Multi-Agent Systems: Technology and Applications. Smart Innovation, Systems and Technologies, vol 58. Springer, Cham. https://doi.org/10.1007/978-3-319-39883-9_28

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-39883-9_28

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-39882-2

  • Online ISBN: 978-3-319-39883-9

  • eBook Packages: EngineeringEngineering (R0)

Publish with us

Policies and ethics