Good News or Bad News? Let the Market Decide

  • Moshe Koppel
  • Itai Shtrimberg
Part of the The Information Retrieval Series book series (INRE, volume 20)


A simple and novel method for generating labeled examples for sentiment analysis is introduced: news stories about publicly traded companies are labeled positive or negative according to price changes of the company stock. It is shown that there are many lexical markers for bad news but none for good news. Overall, learned models based on lexical features can distinguish good news from bad news with accuracy of about 70%. Unfortunately, this result does not yield profits since it works only when stories are labeled according to cotemporaneous price changes but does not work when they are labeled according to subsequent price changes.


sentiment analysis financial analysis automated labelling 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

5. References

  1. Das, S. and Chen, M. (2001) Yahoo for Amazon: Extracting Market Sentiment from Stock Message Boards. In Proceedings of the 8th Asia Pacific Finance Association Annual Conference (APFA 2001), Bangkok, Thailand.Google Scholar
  2. Fama, E. (1970) Efficient Capital Markets: A Review of Theory and Empirical Work. Journal of Finance 25, 383–417.Google Scholar
  3. Finn, A. and Kushmerick, N. (2003) Learning to classify documents according to genre. In IJCAI-03 Workshop on Computational Approaches to Style Analysis and Synthesis, Acapulco, Mexico.Google Scholar
  4. Kushal D., Lawrence, S., and Pennock, D. M. (2003) Mining the peanut gallery: Opinion extraction and semantic classification of product reviews. In Proceedings of the Twelfth International World Wide Web Conference (WWW-2003), 519–528, Budapest, Hungary.Google Scholar
  5. Lavrenko, V., Schmill, M., Lawrie, D., Ogilvie, P., Jensen, D., and Allan, J. (2000) Mining of Concurrent Text and Time Series. In Proceedings of Text Mining Workshop of the Sixth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 37–44, Boston, MA.Google Scholar
  6. Pang, B., Lee, L. and Vaithyanathan, S. (2002) Thumbs up? Sentiment Classification using Machine Learning Techniques. In Proceedings of the 2002 Conference on Empirical Methods in Natural Language Processing (EMNLP), 79–86, Philadelphia, PA.Google Scholar
  7. Seo, Y., Giampapa, J.A., and Sycara, K. (2002) Text Classification for Intelligent Portfolio Management. Technical report CMU-RI-TR-02-14, Robotics Institute, Carnegie Mellon University.Google Scholar
  8. Turney, P. D. (2002) Thumbs Up or Thumbs Down? Semantic Orientation Applied to Unsupervised Classification of Reviews. In Proceedings of ACL 2002, 417–424, Philadelphia, PA.Google Scholar
  9. Wiebe, J., Bruce, R., Bell, M., Martin, M., and Wilson, T. (2001) A Corpus Study of Evaluative and Speculative Language. In Proceedings of 2nd ACL SIGdial Workshop on Discourse and Dialogue. Aalborg, Denmark.Google Scholar
  10. Wiebe, J., Wilson, T., and Bell, M. (2001) Identifying Collocations for Recognizing Opinions. In Proceedings of ACL 01 Workshop on Collocation. Toulouse, France.Google Scholar

Copyright information

© Springer 2006

Authors and Affiliations

  • Moshe Koppel
    • 1
  • Itai Shtrimberg
    • 1
  1. 1.Dept. of Computer ScienceBar-Ilan UniversityRamat-GanIsrael

Personalised recommendations