Do news and sentiment play a role in stock price prediction?

Abstract

Despite continuous improvement in the range and quality of machine learning techniques, accurately predicting stock prices still remains as elusive as ever. We approach this problem using a modern autoregressive neural network architecture and incorporate sentiment predictors, which are becoming increasingly available due to advances in text mining techniques. We find that the inclusion of predictors based on counts of the number of news articles and twitter posts can significantly improve the quality of stock price predictions.

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

Fig. 1
Fig. 2
Fig. 3

References

  1. 1.

    Atsalakis GS, Valavanis KP (2009) Surveying stock market forecasting techniques – part II: soft computing methods. Expert Syst Appl 36:5932–5941

    Article  Google Scholar 

  2. 2.

    Fama E (1965) The behaviour of stock market prices. J Bus 34–105

    Article  Google Scholar 

  3. 3.

    Hyndman RJ, Athanasopoulos G (2013) Forecasting: principles and practice. OTexts, Melbourne

    Google Scholar 

  4. 4.

    Long JBD, Shleifer A, Summers LH, Waldmann RJ (1990) Noise trader risk in financial markets. J Polit Econ 98:703–738

    Article  Google Scholar 

  5. 5.

    Rapach DE, Zhou G (2013) Forecasting stock returns. Handb Econ Forecasting 2:328–383

    Article  Google Scholar 

  6. 6.

    Tetlock PC (2007) Giving content to investor sentiment: the role of Media in the Stock Market. J Financ LXII:1139–1168

    Article  Google Scholar 

  7. 7.

    Vanstone BJ, Gepp A, Harris G (2018) The effect of sentiment on stock price prediction. In: Mouhoub M, Sadaoui S, Mahamed OA, Ali M (eds) Recent trends and future technology in applied intelligence. Springer, Cham, pp 551–559

    Google Scholar 

  8. 8.

    Yen G, Lee C-f (2008) Efficient market hypothesis (EMH): past, present and future. Rev Pac Basin Financ Mark Policies 11:305–329

    Article  Google Scholar 

Download references

Author information

Affiliations

Authors

Corresponding author

Correspondence to Adrian Gepp.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Vanstone, B.J., Gepp, A. & Harris, G. Do news and sentiment play a role in stock price prediction?. Appl Intell 49, 3815–3820 (2019). https://doi.org/10.1007/s10489-019-01458-9

Download citation

Keywords

  • Stock prices
  • Sentiment
  • Auto regressive neural networks
  • News
  • Twitter