Advertisement

Human Computer Interaction with Multivariate Sentiment Distributions of Stocks Intraday

  • Lamarcus ColemanEmail author
  • Mariofanna Milanova
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 1034)

Abstract

In this work we show that the sentiment of the broader stock market, namely the S&P 500, is related to the activity of individual stocks intraday. We introduce a concept we term as embedded context which is an approach to improving unigram language models for restricted use cases. We use a Gaussian Mixture Model to create different sentiment regimes (i.e. distributions) of the broader market over our training period and perform an analysis of the return and volatility characteristics of each stock per each regime. We create an intraday momentum trading strategy using a moving average and Relative Strength Index (RSI) over our testing period with no consideration to our prior sentiment regime analysis which serves as our baseline model. We then create an updated version of our intraday trading strategy which considers the sentiment regime of the broader market. Our results show an improvement in each stock’s intraday strategy performance as a result of considering the broader market’s sentiment regime.

Keywords

Sentiment analysis Gaussian Mixture Model Stock market prediction 

References

  1. 1.
    Bollen, J., Mao, H., Zeng, X.-J.: Twitter mood predicts the stock market. J. Comput. Sci. 2(1), 1–8 (2011).  https://doi.org/10.1016/j.jocs.2010.12.007CrossRefGoogle Scholar
  2. 2.
    Davda, A., Mittal, P.: NLP and Sentiment Driven Automated Trading, p. 41 (2008)Google Scholar
  3. 3.
    Jermann, M.: Predicting Stock Movement through Executive Tweets, p. 9 (n.d.)Google Scholar
  4. 4.
    Kordonis, J., Symeonidis, S., Arampatzis, A.: Stock price forecasting via sentiment analysis on Twitter. In: Proceedings of the 20th Pan-Hellenic Conference on Informatics - PCI 2016, pp. 1–6. ACM Press, Patras (2016).  https://doi.org/10.1145/3003733.3003787
  5. 5.
    Lee, H., Surdeanu, M., MacCartney, B., Jurafsky, D.: On the Importance of Text Analysis for Stock Price Prediction, p. 6 (n.d.)Google Scholar
  6. 6.
    Mittal, A., Goel, A.: Stock Prediction Using Twitter Sentiment Analysis (2011)Google Scholar
  7. 7.
    Nisar, T.M., Yeung, M.: Twitter as a tool for forecasting stock market movements: a short-window event study. J. Financ. Data Sci. 4(2), 101–119 (2018).  https://doi.org/10.1016/j.jfds.2017.11.002CrossRefGoogle Scholar
  8. 8.
    Patel, H.R., Parikh, S.M., Patel, A.M.: Prediction model based on NLP and NN for financial data outcome revelation. Res. J. Comput. Inf. Technol. Sci. 5, 5 (2017)Google Scholar
  9. 9.
    Si, J., Mukherjee, A., Liu, B., Pan, S.J., Li, Q., Li, H.: Exploiting social relations and sentiment for stock prediction. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1139–1145. Association for Computational Linguistics, Doha (2014).  https://doi.org/10.3115/v1/D14-1120
  10. 10.
    Trastour, S., Genin, M., Morlot, A.: Prediction of the crude oil price thanks to natural language processing applied to newspapers, p. 5 (n.d.)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Department of Computer ScienceUniversity of Arkansas at Little RockLittle RockUSA
  2. 2.Gradient Laboratories Inc.Little RockUSA

Personalised recommendations