Abstract
Throughout the past decade, extensive research on text classification has produced fast and accurate algorithms. Most of these algorithms are based on bag-of-words representations, which generate high dimensional data. However, just a few supervised learning methods, such as SVMs, can efficiently handle high dimensional data. To overcome this limitation we propose the use of prior polarity words (PPW) in order to create a compact and representative feature set for financial news classification. Using this approach it is possible to reduce feature sets from thousands to less than tens of features without compromising the accuracy of the text classifier. We measured accuracy, precision, recall, F-measure and ROC AUC of text classifiers using PPW. Classifier using PPW was able to topping all results when compared with a wide range of feature selection methods. By adopting PPW, Support Vector Machines and Naive Bayes performed consistently better than using the full feature set. PPW also turned Naive Bayes comparable to SVMs, as indicated by the improved performance scores in all measures tested.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Bollen, J., Mao, H., Zeng, X.: Twitter mood predicts the stock market. Journal of Computational Science 2(1), 1–8 (2011), http://www.sciencedirect.com/science/article/pii/S187775031100007X
Chan, S.W., Franklin, J.: A text-based decision support system for financial sequence prediction. Decision Support Systems 52(1), 189–198 (2011), http://www.sciencedirect.com/science/article/pii/S0167923611001230
Chang, C.C., Lin, C.J.: Libsvm: A library for support vector machines. ACM Trans. Intell. Syst. Technol. 2(3), 27:1–27:27 (2011), http://doi.acm.org/10.1145/1961189.1961199
Fawcett, T.: An introduction to roc analysis. Pattern Recogn. Lett. 27(8), 861–874 (2006), http://dx.doi.org/10.1016/j.patrec.2005.10.010
Forman, G.: An extensive empirical study of feature selection metrics for text classification. J. Mach. Learn. Res. 3, 1289–1305 (2003), http://dl.acm.org/citation.cfm?id=944919.944974
Gabrilovich, E., Markovitch, S.: Text categorization with many redundant features: Using aggressive feature selection to make svms competitive with c4.5. In: Proceedings of the Twenty-first International Conference on Machine Learning, ICML 2004, p. 41. ACM, New York (2004), http://doi.acm.org/10.1145/1015330.1015388
Groth, S.S., Muntermann, J.: An intraday market risk management approach based on textual analysis. Decision Support Systems 50(4), 680–691 (2011), http://www.sciencedirect.com/science/article/pii/S0167923610001430, (enterprise Risk and Security Management: Data, Text and Web Mining)
Guyon, I., Elisseeff, A.: An introduction to variable and feature selection. J. Mach. Learn. Res. 3, 1157–1182 (2003), http://dl.acm.org/citation.cfm?id=944919.944968
Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., Witten, I.H.: The weka data mining software: An update. SIGKDD Explor. Newsl. 11(1), 10–18 (2009), http://doi.acm.org/10.1145/1656274.1656278
Joachims, T.: Text categorization with suport vector machines: Learning with many relevant features. In: Proceedings of the 10th European Conference on Machine Learning, ECML 1998, Chemnitz, Germany, April 21-23, pp. 137–142 (1998)
Keerthi, S.S., Lin, C.J.: Asymptotic behaviors of support vector machines with gaussian kernel. Neural Comput. 15(7), 1667–1689 (2003), http://dx.doi.org/10.1162/089976603321891855
Mizumoto, K., Yanagimoto, H., Yoshioka, M.: Sentiment analysis of stock market news with semi-supervised learning. In: 2012 IEEE/ACIS 11th International Conference on Computer and Information Science (ICIS), pp. 325–328. IEEE (2012)
Robertson, S.: Understanding inverse document frequency: on theoretical arguments for idf. Journal of Documentation 60(5), 503–520 (2004)
Schumaker, R.P., Chen, H.: Textual analysis of stock market prediction using breaking financial news: The azfin text system. ACM Trans. Inf. Syst. 27(2), 12:1–12:19 (2009), http://doi.acm.org/10.1145/1462198.1462204
Schumaker, R.P., Zhang, Y., Huang, C.N., Chen, H.: Evaluating sentiment in financial news articles. Decis. Support Syst. 53(3), 458–464 (2012), http://dx.doi.org/10.1016/j.dss.2012.03.001
Sebastiani, F.: Machine learning in automated text categorization. ACM Comput. Surv. 34(1), 1–47 (2002), http://doi.acm.org/10.1145/505282.505283
Wilson, T., Hoffmann, P., Somasundaran, S., Kessler, J., Wiebe, J., Choi, Y., Cardie, C., Riloff, E., Patwardhan, S.: Opinionfinder: A system for subjectivity analysis. In: Proceedings of HLT/EMNLP on Interactive Demonstrations, HLT-Demo 2005, pp. 34–35. Association for Computational Linguistics, Stroudsburg (2005), http://dx.doi.org/10.3115/1225733.1225751
Wilson, T., Wiebe, J., Hoffmann, P.: Recognizing contextual polarity in phrase-level sentiment analysis. In: Proceedings of the Conference on Human Language Technology and Empirical Methods in Natural Language Processing, HLT 2005, pp. 347–354. Association for Computational Linguistics, Stroudsburg (2005), http://dx.doi.org/10.3115/1220575.1220619
Wilson, T., Wiebe, J., Hoffmann, P.: Recognizing contextual polarity: An exploration of features for phrase-level sentiment analysis. Comput. Linguist. 35(3), 399–433 (2009), http://dx.doi.org/10.1162/coli.08-012-R1-06-90
Zhang, W., Skiena, S.: Trading strategies to exploit blog and news sentiment. In: ICWSM (2010)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Campos, E., Matsubara, E. (2014). An Experimental Evaluation of Sentiment Analysis on Financial News Using Prior Polarity Words. In: Bazzan, A., Pichara, K. (eds) Advances in Artificial Intelligence -- IBERAMIA 2014. IBERAMIA 2014. Lecture Notes in Computer Science(), vol 8864. Springer, Cham. https://doi.org/10.1007/978-3-319-12027-0_18
Download citation
DOI: https://doi.org/10.1007/978-3-319-12027-0_18
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-12026-3
Online ISBN: 978-3-319-12027-0
eBook Packages: Computer ScienceComputer Science (R0)