Sentiment Analysis for View Modeling

  • Frank Xing
  • Erik Cambria
  • Roy Welsch
Part of the Socio-Affective Computing book series (SAC, volume 9)


This chapter investigates a method to incorporate market sentiment to asset allocation models. In the previous chapter, we experimented with robust mean-variance optimization, which is a static process that finds the status quo optimal portfolio weights and surfs market fluctuations. However, an important piece of the jigsaw is missing, i.e., the irrational components in rise and fall of asset prices. In fact, if all the market participants hold the same robust Markowitz portfolio, the market would not clear, nor would transactions happen. The Black-Litterman model provides us an entry to include subjective views to asset allocation models. As an extension to it, concept-level sentiment analysis methods described in this chapter will be used to compute the subjective views, emulating a financial analyst’s activities.


Concept-level sentiment analysis Subjective view modeling Market sentiment The Black-Litterman model Sentic computing ECM-LSTM 


  1. 3.
    W. Antweiler, M.Z. Frank, Is all that talk just noise? The information content of internet stock message boards. J. Financ. 59(3), 1259–1294 (2004)Google Scholar
  2. 5.
    S. Baccianella, A. Esuli, F. Sebastiani, Sentiwordnet 3.0: an enhanced lexical resource for sentiment analysis and opinion mining, in 7th Language Resources and Evaluation Conference, 2010, pp. 2200–2204Google Scholar
  3. 8.
    S. Banerjee, R. Kaniel, I. Kremer, Price drift as an outcome of differences in higher-order beliefs. Rev. Financ. Stud. 22(9), 3707–3734 (2009)CrossRefGoogle Scholar
  4. 14.
    F. Black, R. Litterman, Asset allocation: combining investor view with market equilibrium. J. Fixed Income 1, 7–18 (1991)CrossRefGoogle Scholar
  5. 18.
    J. Bollen, H. Mao, A. Pepe, Modeling public mood and emotion: Twitter sentiment and socio-economic phenomena, in Proceedings of the Fifth International AAAI Conference on Weblogs and Social Media, 2011Google Scholar
  6. 19.
    J. Bollen, H. Mao, X. Zeng, Twitter mood predicts the stock market. J. Comput. Sci. 2(1), 1–8 (2011)CrossRefGoogle Scholar
  7. 24.
    E. Cambria, An introduction to concept-level sentiment analysis, in Mexican International Conference on Artificial Intelligence (LNCS), vol. 8266, 2013, pp. 478–483Google Scholar
  8. 25.
    E. Cambria, Affective computing and sentiment analysis. IEEE Intell. Syst. 31(2), 102–107 (2016)CrossRefGoogle Scholar
  9. 26.
    E. Cambria, A. Hussain, Sentic Computing: A Common-Sense-Based Framework for Concept-Level Sentiment Analysis (Springer International Publishing, Cham, 2015)CrossRefGoogle Scholar
  10. 27.
    E. Cambria, A. Livingstone, A. Hussain, The hourglass of emotions, in Lecture Notes in Computer Science, vol. 7403 (Springer, Berlin, 2012), pp. 144–157Google Scholar
  11. 28.
    E. Cambria, S. Poria, D. Hazarika, K. Kwok, Senticnet 5: discovering conceptual primitives for sentiment analysis by means of context embeddings, in The Thirty-Second AAAI Conference on Artificial Intelligence, 2018, pp. 1795–1802Google Scholar
  12. 29.
    E. Cambria, D. Rajagopal, K. Kwok, J. Sepulveda, Gecka: game engine for commonsense knowledge acquisition, in The Twenty-Eighth International Flairs Conference, 2015, pp. 282–287Google Scholar
  13. 46.
    M.-C. de Marneffe, C.D. Manning, The Stanford typed dependencies representation, in Coling 2008: Proceedings of the Workshop on Cross-Framework and Cross-Domain Parser Evaluation, 2008, pp. 1–8Google Scholar
  14. 48.
    R. Dey, F.M. Salem, Gate-variants of gated recurrent unit (GRU) neural networks, in IEEE 60th International Midwest Symposium on Circuits and Systems (MWSCAS), 2017, pp. 1597–1600Google Scholar
  15. 56.
    E.F. Fama, K.R. French, A five-factor asset pricing model. J. Financ. Econ. 116, 1–22 (2015)CrossRefGoogle Scholar
  16. 58.
    R. Feldman, Techniques and applications for sentiment analysis. Commun. ACM 56(4), 82–89 (2013)CrossRefGoogle Scholar
  17. 60.
    C. Fellbaum, WordNet: An Electronic Lexical Database (MIT Press, Cambridge, 1998)CrossRefGoogle Scholar
  18. 64.
    J. Gagnon, S. Goyal, Networks, markets, and inequality. Am. Econ. Rev. 107(1), 1–30 (2017)CrossRefGoogle Scholar
  19. 65.
    F.A. Gers, D. Eck, J. Schmidhuber, Applying LSTM to Time Series Predictable Through Time-Window Approaches (Springer, London, 2002), pp. 193–200Google Scholar
  20. 67.
    K. Greff, R.K. Srivastava, J. Koutnik, B.R. Steunebrink, J. Schmidhuber, LSTM: a search space odyssey. IEEE Trans. Neural Netw. Learn. Syst. 28(10), 2222–2232 (2017)PubMedCrossRefGoogle Scholar
  21. 69.
    R.V. Guha, D.B. Lenat, Cyc: a midterm report. AI Mag. 11(3), 32–59 (1990)Google Scholar
  22. 70.
    W.L. Hamilton, K. Clark, J. Leskovec, D. Jurafsky, Inducing domain-specific sentiment lexicons from unlabeled corpora, in Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2016, pp. 595–605Google Scholar
  23. 72.
    G. He, R. Litterman, The intuition behind black-Litterman model portfolios. Goldman Sachs working paper (1999).
  24. 73.
    E. Henry, Are investors influenced by how earnings press releases are written? Int. J. Bus. Commun. 45, 363–407 (2008)CrossRefGoogle Scholar
  25. 74.
    M. Hentschel, O. Alonso, Follow the money: a study of cashtags on Twitter. First Monday 19(8) (2014).
  26. 75.
    S. Hochreiter, J. Schmidhuber, Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)CrossRefGoogle Scholar
  27. 76.
    M. Hu, B. Liu, Mining and summarizing customer reviews, in Proceedings of the Tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2004, pp. 168–177Google Scholar
  28. 80.
    R. Jensen, The digital provide: information (technology), market performance, and welfare in the south Indian fisheries sector. Q. J. Econ. 122(3), 879–924 (2007)CrossRefGoogle Scholar
  29. 83.
    N.K. Kasabov, Q. Song, Denfis: dynamic evolving neural-fuzzy inference system and its application for time-series prediction. IEEE Trans. Fuzzy Syst. 10, 144–154 (2002)CrossRefGoogle Scholar
  30. 84.
    E.F. Kelly, Computer Recognition of English Word Senses (North-Holland Publishing Co, Amsterdam, 1975)Google Scholar
  31. 95.
    Q. Li, L. Jiang, P. Li, H. Chen, Tensor-based learning for predicting stock movements, in Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence, Austin, 2015, pp. 1784–1790Google Scholar
  32. 100.
    H. Liu, P. Singh, Conceptnet – a practical commonsense reasoning tool-kit. BT Technol. J. 22(4), 211–226 (2004)CrossRefGoogle Scholar
  33. 103.
    T. Loughran, B. McDonald, When is a liability not a liability? Textual analysis, dictionaries, and 10-ks. J. Financ. 66, 67–97 (2011)CrossRefGoogle Scholar
  34. 106.
    S. Makridakis, M. Hibon, The M3-competition: results, conclusions and implications. Int. J. Forecast. 16(4), 451–476 (2000)CrossRefGoogle Scholar
  35. 109.
    S. Marsella, J. Gratch, Computationally modeling human emotion. Commun. ACM 57(12), 56–67 (2014)CrossRefGoogle Scholar
  36. 119.
    S. Morris, A. Postlewaite, H.S. Shin, Depth of knowledge and the effect of higher order uncertainty. Econ. Theory 6(3), 453–467 (1995)CrossRefGoogle Scholar
  37. 124.
    M. Nofer, O. Hinz, Using Twitter to predict the stock market: where is the mood effect? Bus. Inf. Syst. Eng. 57(4), 229–242 (2015)CrossRefGoogle Scholar
  38. 127.
    J. Owyang, The future of the social web, 2009, Technical Report available at
  39. 130.
    P.N. Pant, W.H. Starbuck, Innocents in the forest: forecasting and research methods. J. Manag. 16(2), 433–460 (1990)Google Scholar
  40. 133.
    R. Plutchik, The nature of emotions: human emotions have deep evolutionary roots, a fact that may explain their complexity and provide tools for clinical practice. Am. Sci. 89(4), 344–350 (2001)CrossRefGoogle Scholar
  41. 134.
    S. Poria, E. Cambria, A. Gelbukh, F. Bisio, A. Hussain, Sentiment data flow analysis by means of dynamic linguistic patterns. IEEE Comput. Intell. Mag. 10(4), 26–36 (2015)CrossRefGoogle Scholar
  42. 136.
    S. Poria, E. Cambria, G. Winterstein, G.-B. Huang, Sentic patterns: dependency-based rules for concept-level sentiment analysis. Knowl. Based Syst. 69, 45–63 (2014)CrossRefGoogle Scholar
  43. 144.
    I.A. Sag, T. Baldwin, F. Bond, A. Copestake, D. Flickinger, Multiword expressions: a pain in the neck for NLP. Lect. Notes Comput. Sci 2276, 1–15 (2002)CrossRefGoogle Scholar
  44. 146.
    S. Satchell, A. Scowcroft, A demystification of the black-Litterman model: managing quantitative and traditional portfolio construction. J. Asset Manag. 1(2), 138–150 (2000)CrossRefGoogle Scholar
  45. 148.
    R.P. Schumaker, H. Chen, Textual analysis of stock market prediction using breaking financial news: the AZFinText system. ACM Trans. Inf. Syst. 27(2), 12:1–12:19 (2009)Google Scholar
  46. 151.
    S. Shacham, A shortened version of the profile of mood states. J. Pers. Assess. 47(3), 305–306 (1983)PubMedCrossRefGoogle Scholar
  47. 157.
    J. Smailović, Sentiment Analysis in Streams of Microblogging Posts. Ph.D thesis, Jožef Stefan Institute, 2014Google Scholar
  48. 158.
    F.A. Sortino, L.N. Price, Performance measurement in a downside risk framework. J. Invest. 3, 59–64 (1994)CrossRefGoogle Scholar
  49. 160.
    R. Speer, C. Havasi, Representing general relational knowledge in conceptnet 5, in Language Resources and Evaluation Conference (LREC), 2012, pp. 3679–3686Google Scholar
  50. 162.
    C. Strapparava, A. Valitutti, Wordnet-affect: an affective extension of wordnet, in Language Resources and Evaluation Conference (LREC), 2004Google Scholar
  51. 165.
    Y. Tai, H. Kao, Automatic domain-specific sentiment lexicon generation with label propagation, in The 15th International Conference on Information Integration and Web-Based Applications & Services, 2013, p. 53Google Scholar
  52. 169.
    T. Tieleman, G.E. Hinton, Lecture 6.5-rmsprop: divide the gradient by a running average of its recent magnitude. COURSERA: Neural Networks for Machine Learning (2012)Google Scholar
  53. 177.
    R. Valitutti, Wordnet-affect: an affective extension of wordnet, in In Proceedings of the 4th International Conference on Language Resources and Evaluation, 2004, pp. 1083–1086Google Scholar
  54. 182.
    A. Weichselbraun, S. Gindl, F. Fischer, S. Vakulenko, A. Scharl, Aspect-based extraction and analysis of affective knowledge from social media streams. IEEE Intell. Syst. 32(3), 80–88 (2017)CrossRefGoogle Scholar
  55. 184.
    T. Wilson, P. Hoffmann, S. Somasundaran, J. Kessler, J. Wiebe, Y. Choi, C. Cardie, E. Riloff, S. Patwardhan, Opinionfinder: a system for subjectivity analysis, in Empirical Methods in Natural Language Processing (EMNLP) (Springer, New York, 2005)CrossRefGoogle Scholar
  56. 187.
    B. Wuthrich, V. Cho, S. Leung, D. Permunetilleke, K. Sankaran, J. Zhang, Daily stock market forecast from textual web data, in IEEE International Conference on Systems, Man, and Cybernetics, vol. 3, 1998, pp. 2720–2725Google Scholar
  57. 188.
    F.Z. Xing, E. Cambria, L. Malandri, C. Vercellis, Discovering Bayesian market views for intelligent asset allocation, in European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD), 2018Google Scholar
  58. 189.
    F.Z. Xing, E. Cambria, R.E. Welsch, Intelligent Bayesian asset allocation via market sentiment views. IEEE Comput. Intell. Mag. 13(4), 25–34 (2018)CrossRefGoogle Scholar
  59. 192.
    F.Z. Xing, E. Cambria, Y. Zhang, Sentiment-aware volatility forecasting. Knowl. Based Syst. 176, 68–76 (2019)CrossRefGoogle Scholar
  60. 193.
    F.Z. Xing, E. Cambria, X. Zou, Predicting evolving chaotic time series with fuzzy neural networks, in International Joint Conference on Neural Networks (IJCNN), 2017, pp. 3176–3183Google Scholar
  61. 198.
    A. Yoshihara, K. Seki, K. Uehara, Leveraging temporal properties of news events for stock market prediction. Artif. Intell. Res. 5(1), 103–110 (2016)Google Scholar
  62. 201.
    W. Zhang, S. Skiena, Trading strategies to exploit blog and news sentiment, in Proceedings of the Fourth International AAAI Conference on Weblogs and Social Media (ICWSM), Washington, DC, 2010, pp. 375–378Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Frank Xing
    • 1
  • Erik Cambria
    • 1
  • Roy Welsch
    • 2
  1. 1.School of Computer Science and EngineeringNanyang Technological UniversitySingaporeSingapore
  2. 2.Sloan School of ManagementMassachusetts Institute of TechnologyCambridgeUSA

Personalised recommendations