Abstract
With the fast development of the Internet, especially the development of the Web technique, more and more people express their views on the Internet. The content of these views involve various aspects of our life, such as books, movies, musics, policies, commodities, technical services, etc. Since these views are usually subjective and possess great potential commercial and social value, the study of sentiment analysis is followed. At the early stage of sentiment analysis, researchers used lexicon based method to solve sentiment analysis problem. With the improvement in machine learning and Natural Language Processing technology, machine learning based method are becoming more and more popular in the field of sentiment analysis. In this study, we propose an ensemble sentiment classification model based on three multi-classifier systems. The proposed model uses majority voting as an ensemble method of multiple multi-classifier systems. The effectiveness of the classification model is verified on five public datasets. Experimental results show that the proposed model is superior to traditional sentiment classification methods and simple multi-classifier systems in the performance of classification accuracy. By using the sentiment classification model proposed in this paper, the accuracy improvement in different domains also show that our proposed model has certain generalization ability.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bo, P., Lee, L.: A sentimental education: sentiment analysis using subjectivity summarization based on minimum cuts. In: Meeting on Association for Computational Linguistics, p. 271 (2004)
Breiman, L.: Bagging predictors. Mach. Learn. 24(2), 123–140 (1996)
Catal, C., Nangir, M.: A sentiment classification model based on multiple classifiers. Appl. Soft Comput. 50, 135–141 (2017)
Fang, Y., Tan, H., Zhang, J.: Multi-strategy sentiment analysis of consumer reviews based on semantic fuzziness. IEEE Access PP(99), 1 (2018)
Fersini, E., Messina, E., Pozzi, F.A.: Sentiment analysis: Bayesian ensemble learning. Decis. Support Syst. 68, 26–38 (2014)
Ho, T.K.: The random subspace method for constructing decision forest. IEEE Trans. Pattern Anal. Mach. Intell. 20(8), 832–844 (1998)
Júnior, E.A.C., Marinho, V.Q., Santos, L.B.D.: NILC-USP at SemEval-2017 task 4: a multi-view ensemble for twitter sentiment analysis, pp. 611–615 (2017)
Li, Y.M., Li, T.Y.: Deriving market intelligence from microblogs. Decis. Support Syst. 55(1), 206–217 (2013)
Liu, B.: Sentiment Analysis and Opinion Mining. Morgan & Claypool Publishers, San Rafael (2012)
Onan, A., Korukoǧlu, S., Bulut, H.: A multiobjective weighted voting ensemble classifier based on differential evolution algorithm for text sentiment classification. Expert Syst. Appl. 62, 1–16 (2016)
Ortigosa, A., Martn, J.M., Carro, R.M.: Sentiment analysis in Facebook and its application to e-learning. Comput. Hum. Behav. 31(1), 527–541 (2014)
Pang, B., Lee, L., Vaithyanathan, S.: Thumbs up? Sentiment classification using machine learning techniques. In: Empirical Methods Natural Language Processing, pp. 79–86 (2002)
Priore, P., Ponte, B., Puente, J., Gomez, A.: Learning-based scheduling offlexible manufacturing systems using ensemble methods. Comput. Ind. Eng. 126 (2018)
Ramisch, C.: Application 1: lexicography. In: Multiword Expressions Acquisition. TANLP, pp. 159–179. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-09207-2_6
Silva, N.F.F.D., Hruschka Jr., E.R., Hruschka, E.R.: Tweet sentiment analysis with classifier ensembles. Decis. Support Syst. 66, 170–179 (2014)
Tripathy, A., Agrawal, A., Rath, S.K.: Classification of sentiment reviews using n-gram machine learning approach. Expert Syst. Appl. 57(C), 117–126 (2016)
Wang, G., Sun, J., Ma, J., Xu, K., Gu, J.: Sentiment classification: the contribution of ensemble learning. Decis. Support Syst. 57(1), 77–93 (2014)
Whitehead, M., Yaeger, L.: Building a general purpose cross-domain sentiment mining model. In: 2009 WRI World Congress on Computer Science and Information Engineering, pp. 472–476 (2009)
Whitehead, M., Yaeger, L.: Sentiment mining using ensemble classification models. In: Sobh, T. (ed.) Innovations and Advances in Computer Sciences and Engineering, vol. I, pp. 509–514. Springer, Dordrecht (2010). https://doi.org/10.1007/978-90-481-3658-2_89
Xia, R., Zong, C., Li, S.: Ensemble of feature sets and classification algorithms for sentiment classification. Inf. Sci. 181(6), 1138–1152 (2011)
Xiong, Z., Shen, Q., Wang, Y., Zhu, C.: Paragraph vector representation based on word to vector and CNN learning. Comput. Mater. Continua 55, 213–227 (2018)
Zhang, Y., Wang, Q., Li, Y., Wu, X.: Sentiment classification based on piecewise pooling convolutional neural network. Comput. Mater. Continua 56, 285–297 (2018)
Zhou, Z.: Ensemble Methods: Foundations and Algorithms. Taylor & Francis, New York (2012)
Acknowledgement
We would like to express our gratitude to Innovation Base Project for Graduates (Research of Security Embedded System) for its support.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Yang, K., Liao, C., Zhang, W. (2019). A Sentiment Classification Model Based on Multiple Multi-classifier Systems. In: Sun, X., Pan, Z., Bertino, E. (eds) Artificial Intelligence and Security. ICAIS 2019. Lecture Notes in Computer Science(), vol 11633. Springer, Cham. https://doi.org/10.1007/978-3-030-24265-7_25
Download citation
DOI: https://doi.org/10.1007/978-3-030-24265-7_25
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-24264-0
Online ISBN: 978-3-030-24265-7
eBook Packages: Computer ScienceComputer Science (R0)