Increasing the Explanatory Power of Investor Sentiment Analysis for Commodities in Online Media

  • Achim KleinEmail author
  • Martin Riekert
  • Lyubomir Kirilov
  • Joerg Leukel
Conference paper
Part of the Lecture Notes in Business Information Processing book series (LNBIP, volume 320)


Online media are an important source for investor sentiment on commodities. Although there is empirical evidence for a relationship between investor sentiment from news and commodity returns, the impact of classifier design on the explanatory power of sentiment for returns has received little attention. We evaluate the explanatory power of nine classifier designs and find that (1) a positive relationship holds between more opinionated online media sentiment and commodity returns, (2) weighting dictionary terms by machine learning increases explanatory power by up to 25%, and (3) the commonly used dictionary of Loughran and McDonald is detrimental for commodity sentiment analysis.


Investor sentiment Online media Classifier design Explanatory power Commodity returns 


  1. 1.
    Shleifer, A.: Inefficient Markets: An Introduction to Behavioral Finance. Oxford University Press, New York (2000)CrossRefGoogle Scholar
  2. 2.
    Feuerriegel, S., Neumann, D.: News or noise? How news drives commodity prices. In: Proceedings of the 34th International Conference on Information Systems (ICIS 2013), Milan, Italy, pp. 1–20 (2013)Google Scholar
  3. 3.
    Feuerriegel, S., Heitzmann, S.F., Neumann, D.: Do investors read too much into news? How news sentiment causes price formation. In: Proceedings of the 48th Hawaii International Conference on System Sciences (HICSS’ 2015), pp. 4803–4812 (2015)Google Scholar
  4. 4.
    Smales, L.A.: News sentiment in the gold futures market. J. Bank. Finan. 49, 275–286 (2014)CrossRefGoogle Scholar
  5. 5.
    Borovkova, S., Mahakena, D.: News, volatility and jumps: the case of natural gas futures. Quant. Finan. 15(7), 1217–1242 (2015)MathSciNetCrossRefGoogle Scholar
  6. 6.
    Alfano, S., Feuerriegel, S., Neumann, D.: Is news sentiment more than just noise? In: Proceedings of the 23rd European Conference on Information Systems (ECIS 2015), Münster, Germany, pp. 1–16 (2015)Google Scholar
  7. 7.
    Clements, A.E., Todorova, N.: Information flow, trading activity and commodity futures volatility. J. Futures Markets 36(1), 88–104 (2016)CrossRefGoogle Scholar
  8. 8.
    Feuerriegel, S., Lampe, M.W., Neumann, D.: News processing during speculative bubbles: evidence from the oil market. In: Proceedings of the 47th Hawaii International Conference on System Sciences (HICSS 2014), pp. 4103–4112 (2014)Google Scholar
  9. 9.
    Loughran, T., McDonald, B.: When is a liability not a liability? Textual analysis, dictionaries, and 10-Ks. J. Finan. 66(1), 67–97 (2011)CrossRefGoogle Scholar
  10. 10.
    Salton, G., Buckley, C.: Term-weighting approaches in automatic text retrieval. Inf. Process. Manage. 24(5), 513–523 (1988)CrossRefGoogle Scholar
  11. 11.
    Pang, B., Lee, L., Vaithyanathan, S.: Thumbs up? Sentiment classification using machine learning techniques. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP 2002), Philadelphia, PA, USA, pp. 79–86 (2002)Google Scholar
  12. 12.
    Sebastiani, F.: Machine learning in automated text categorization. ACM Comput. Surv. 34(1), 1–47 (2002)CrossRefGoogle Scholar
  13. 13.
    Wang, S., Manning, C.D.: Baselines and bigrams: simple, good sentiment and topic classification. In: Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics-Volume 2, Jeju, South Korea, vol. 94305, pp. 90–94 (2012)Google Scholar
  14. 14.
    Rao, T., Srivastava, S.: Modeling movements in oil, gold, forex and market indices using search volume index and Twitter sentiments. In: Proceedings of the 5th Annual ACM Web Science Conference, Paris, France, pp. 336–345 (2013)Google Scholar
  15. 15.
    Loughran, T., McDonald, B.: Loughran and McDonald financial sentiment dictionaries (2014).
  16. 16.
    Henry, E.: Are investors influenced by how earnings press releases are written? J. Bus. Commun. 45(4), 363–407 (2008)CrossRefGoogle Scholar
  17. 17.
    Brown, G.W., Cliff, M.T.: Investor sentiment and asset valuation. J. Bus. 78(2), 405–440 (2005)CrossRefGoogle Scholar
  18. 18.
    Baker, M., Wurgler, J.: Investor sentiment and the cross-section of stock returns. J. Finan. 61(4), 1645–1680 (2006)CrossRefGoogle Scholar
  19. 19.
    Pan, J., Poteshman, A.M.: The information in option volume for future stock prices. Rev. Finan. Stud. 19(3), 871–908 (2006)CrossRefGoogle Scholar
  20. 20.
    Joachims, T.: Text categorization with support vector machines: learning with many relevant features. In: Nédellec, C., Rouveirol, C. (eds.) ECML 1998. LNCS, vol. 1398, pp. 137–142. Springer, Heidelberg (1998). Scholar
  21. 21.
    Klein, A., Altuntas, O., Riekert, M., Dinev, V.: Combined approach for extracting object-specific investor sentiment from weblogs. In: Proceedings of the 11th International Conference on Wirtschaftsinformatik (WI 2013), Leipzig, Germany, pp. 691–705 (2013)Google Scholar
  22. 22.
    Shleifer, A., Summers, L.H.: The noise trader approach to finance. J. Econ. Perspect. 4(2), 19–33 (1990)CrossRefGoogle Scholar
  23. 23.
    Shleifer, A., Vishny, R.W.: The limits of arbitrage. J. Finan. 52(1), 35–55 (1997)CrossRefGoogle Scholar
  24. 24.
    Barberis, N., Thaler, R.: A survey of behavioral finance. In: Handbook of the Economics of Finance, vol. 1, pp. 1053–1128 (2003)Google Scholar
  25. 25.
    Lewis, D.D., Rose, T.G., Li, F., Yang, Y., Rose, T.G., Li, F.: RCV1: a new benchmark collection for text categorization research. J. Mach. Learn. Res. 5, 361–397 (2004)Google Scholar
  26. 26.
    Dadvar, M., Hauff, C., de Jong, F.: Scope of negation detection in sentiment analysis. In: Proceedings of the Dutch-Belgian Information Retrieval Workshop, pp. 16–20 (2011)Google Scholar
  27. 27.
    Riekert, M., Leukel, J., Klein, A.: Online media sentiment: understanding machine learning-based classifiers. In: Proceedings of the 24th European Conference on Information Systems (ECIS 2016), Istanbul, Turkey (2016)Google Scholar
  28. 28.
    Fan, R., Chang, K., Hsieh, C.: LIBLINEAR: a library for large linear classification. J. Mach. Learn. Res. 9, 1871–1874 (2008)zbMATHGoogle Scholar
  29. 29.
    Tang, H., Tan, S., Cheng, X.: A survey on sentiment detection of reviews. Expert Syst. Appl. 36(7), 10760–10773 (2009)CrossRefGoogle Scholar
  30. 30.
    Hastie, T., Tibshirani, R., Friedman, J.: The Elements of Statistical Learning: Data Mining, Inference, and Prediction, Second Edition. Springer Series in Statistics, 2nd edn. Springer, Heidelberg (2009). Scholar
  31. 31.
    Leopold, E., Kindermann, J.: Text categorization with support vector machines. How to represent texts in input space? Mach. Learn. 46(1–3), 423–444 (2002)CrossRefGoogle Scholar
  32. 32.
    Lombardi, P., Aprile, G., Gsell, M., Winter, A., Reinhardt, M., Queck, S.: D1.1 definition of market surveillance, risk management and retail brokerage usecases (2011)Google Scholar
  33. 33.
    Antweiler, W., Frank, M.Z.: Is all that talk just noise? The information content of Internet stock message boards. J. Finan. 59(3), 1259–1294 (2004)CrossRefGoogle Scholar
  34. 34.
    Steiger, J.H.: Tests for comparing elements of a correlation matrix. Psychol. Bull. 87(2), 245–251 (1980)MathSciNetCrossRefGoogle Scholar
  35. 35.
    Pröllochs, N., Feuerriegel, S., Neumann, D.: Generating domain-specific dictionaries using Bayesian learning. In: Proceedings of the 23rd European Conference on Information Systems (ECIS 2015), pp. 1–14 (2015)Google Scholar
  36. 36.
    Bollen, J., Mao, H., Zeng, X.: Twitter mood predicts the stock market. J. Comput. Sci. 2(1), 1–8 (2011)CrossRefGoogle Scholar
  37. 37.
    Das, S.R., Chen, M.Y.: Yahoo! For Amazon: sentiment extraction from small talk on the Web. Manage. Sci. 53(9), 1375–1388 (2007)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  • Achim Klein
    • 1
    Email author
  • Martin Riekert
    • 1
  • Lyubomir Kirilov
    • 1
  • Joerg Leukel
    • 1
  1. 1.Information Systems 2University of HohenheimStuttgartGermany

Personalised recommendations