Measuring sentiment orientation and utility in short text messages
Keywords:
language-independent, text analysis, classification, opinion miningAbstract
The main framework of this paper is the opinion mining, a special area of text mining. The holder of an opinion believes a claim about a topic, and he associates a good or a bad sentiment with his belief. This negative, positive or neutral orientation of the opinion can be detected based on the text messages of the holder. The utility of a comment can be described as the magnitude of the effect of the message on the readers’ opinion. E. g. if a message has higher utility, it has a greater chance to influence the effective demand for a product. So utility is a measure of weighting of messages in calculations. We examined the orientation and utility valuation of short text messages through two methodological approaches: Support Vector Machines (SVM), and Artificial Neural Networks (NN) learning algorithms. We find that the efficiency of the automatic classification of orientation and utility values differs from each other using both methodologies. So we concluded that both of these measures represent different type of connection with the content of the texts. So we examine the opportunity of improving accuracy of classification by including additional measures.
References
Borgulya, I. (1998): Neurális hálók és fuzzy-rendszerek. Dialóg Campus: Pécs, 226 p. Cotton, N. J., Wilamowski, B. M. (2011): Compensation of Nonlinearities Using Neural Networks Implemented on Inexpensive Microcontrollers. IEEE Transactions on Industrial Electronics, 58(3), 733–740. https://doi.org/10.1109/TIE.2010.2098377
Crammer, K., Singer, Y., Cristianini, N., Shawe-Taylor, J., Williamson, B. (2001): On the algorithmic implementation of multiclass kernel-based vector machines. Journal of Machine Learning Research, 2. 265–292.
Fan, R. E., Chen, P. H., Lin, C. J. (2005): Working set selection using second order information for training SVM. Journal of Machine Learning Research, 6. 1889–1918.
Hanke, M., Halchenko, Y. O., Sederberg, P. B., Hanson, S. J., Haxby, J. V., Pollmann, S. (2009): PyMVPA: A Python toolbox for multivariate pattern analysis of fMRI data. Neuroinformatics, 7. 37–53. https://doi.org/10.1007/s12021-008-9041-y
Kryzanowski, L., Galler, M., Wright, D. W. (1993): Using Artificial Neural Networks to Pick Stocks. Financial Analysts Journal, 49(4), 21. https://doi.org/10.2469/faj.v49.n4.21
Kushal, D., Lawrence, S., Pennock, D. M. (2003): Mining the peanut gallery: Opinion extraction and semantic classification of product reviews. In: Proceedings of WWW-03, 519–528. p. https://doi.org/10.1145/775152.775226
Liu, B. (2010): Handbook of Natural Language Processing. 2nd Edition, CRC Press LCC, ISBN13 9781420085938, 627–660. p.
Nissen, S. (2003): Implementation of a Fast Artificial Neural Network Library, Report 31. Department of Computer Science University of Copenhagen (DIKU) 1–88. p.
Pang, B., Lee, L. (2008): Opinion mining and sentiment analysis. In Foundations and Trends in Information Retrieval, 2(1–2), 1–135. https://doi.org/10.1561/9781601981516
Qin, Y., Wang, X. (2009): Study on Multi-label Text Classification Based on SVM. Fuzzy Systems and Knowledge Discovery, 2009. FSKD '09. Sixth International Conference on, ISBN: 978-0-7695-3735-1, 300–304. https://doi.org/10.1109/FSKD.2009.207
Tikk, D. (szerk.) (2007): Szövegbányászat. Typotex: Budapest, 294. p.
Walczak, S. (2001): An Empirical Analysis of Data Requirements for Financial Forecasting with Neural Networks. Journal of Management Information Systems, 17(4), 203–222. https://doi.org/10.1080/07421222.2001.11045659
Downloads
Published
Issue
Section
License
Copyright (c) 2011 Kovács Balázs, Kruzslicz Ferenc
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
