FBSEM: A Novel Feature-Based Stacked Ensemble Method for Sentiment Analysis

Автор: Yasin Görmez, Yunus E. Işık, Mustafa Temiz, Zafer Aydın

Журнал: International Journal of Information Technology and Computer Science @ijitcs

Статья в выпуске: 6 Vol. 12, 2020 года.

Бесплатный доступ

Sentiment analysis is the process of determining the attitude or the emotional state of a text automatically. Many algorithms are proposed for this task including ensemble methods, which have the potential to decrease error rates of the individual base learners considerably. In many machine learning tasks and especially in sentiment analysis, extracting informative features is as important as developing sophisticated classifiers. In this study, a stacked ensemble method is proposed for sentiment analysis, which systematically combines six feature extraction methods and three classifiers. The proposed method obtains cross-validation accuracies of 89.6%, 90.7% and 67.2% on large movie, Turkish movie and SemEval-2017 datasets, respectively, outperforming the other classifiers. The accuracy improvements are shown to be statistically significant at the 99% confidence level by performing a Z-test.

Еще

Sentiment analysis, ensemble methods, machine learning, feature extraction

Короткий адрес: https://sciup.org/15017471

IDR: 15017471   |   DOI: 10.5815/ijitcs.2020.06.02

Список литературы FBSEM: A Novel Feature-Based Stacked Ensemble Method for Sentiment Analysis

  • Kaynar, O., Aydin, Z., Görmez, Y., 2017. Sentiment Analizinde Öznitelik Düşürme Yöntemlerinin Oto Kodlayıcılı Derin Öğrenme Makinaları ile Karşılaştırılması. Bilişim Teknol. Derg. 10, 319–326. https://doi.org/10.17671/gazibtd.331046
  • Li, J., Sun, M., 2007. Experimental Study on Sentiment Classification of Chinese Review using Machine Learning Techniques, in: 2007 International Conference on Natural Language Processing and Knowledge Engineering. Presented at the 2007 International Conference on Natural Language Processing and Knowledge Engineering, pp. 393–400. https://doi.org/10.1109/NLPKE.2007.4368061
  • Go, A., Bhayani, R., Huang, L., 2009a. Twitter Sentiment Classification using Distant Supervision.
  • Mouthami, K., Devi, K.N., Bhaskaran, V.M., 2013. Sentiment analysis and classification based on textual reviews, in: 2013 International Conference on Information Communication and Embedded Systems (ICICES). Presented at the 2013 International Conference on Information Communication and Embedded Systems (ICICES), pp. 271–276. https://doi.org/10.1109/ICICES.2013.6508366
  • Gautam, G., Yadav, D., 2014. Sentiment analysis of twitter data using machine learning approaches and semantic analysis, in: 2014 Seventh International Conference on Contemporary Computing (IC3). Presented at the 2014 Seventh International Conference on Contemporary Computing (IC3), pp. 437–442. https://doi.org/10.1109/IC3.2014.6897213
  • Nizam, H., Akın, S.S., 2014. Sosyal Medyada Makine Öğrenmesi ile Duygu Analizinde Dengeli ve Dengesiz Veri Setlerinin Performanslarının Karşılaştırılması. Presented at the XIX. Türkiye’de İnternet Konferansı, p. 6.
  • Çoban, Ö., Özyer, B., Özyer, G.T., 2015. Sentiment analysis for Turkish Twitter feeds, in: 2015 23nd Signal Processing and Communications Applications Conference (SIU). Presented at the 2015 23nd Signal Processing and Communications Applications Conference (SIU), pp. 2388–2391. https://doi.org/10.1109/SIU.2015.7130362
  • Kranjc, J., Smailović, J., Podpečan, V., Grčar, M., Žnidaršič, M., Lavrač, N., 2015. Active learning for sentiment analysis on data streams: Methodology and workflow implementation in the ClowdFlows platform. Inf. Process. Manag. 51, 187–203. https://doi.org/10.1016/j.ipm.2014.04.001
  • Tripathy, A., Agrawal, A., Rath, S.K., 2016. Classification of sentiment reviews using n-gram machine learning approach. Expert Syst. Appl. 57, 117–126. https://doi.org/10.1016/j.eswa.2016.03.028
  • Rohini, V., Thomas, M., Latha, C.A., 2016. Domain based sentiment analysis in regional Language-Kannada using machine learning algorithm, in: 2016 IEEE International Conference on Recent Trends in Electronics, Information Communication Technology (RTEICT). Presented at the 2016 IEEE International Conference on Recent Trends in Electronics, Information Communication Technology (RTEICT), pp. 503–507. https://doi.org/10.1109/RTEICT.2016.7807872
  • Hassan, A., Mahmood, A., 2017. Deep Learning approach for sentiment analysis of short texts, in: 2017 3rd International Conference on Control, Automation and Robotics (ICCAR). Presented at the 2017 3rd International Conference on Control, Automation and Robotics (ICCAR), pp. 705–710. https://doi.org/10.1109/ICCAR.2017.7942788
  • Al-Smadi, M., Qawasmeh, O., Al-Ayyoub, M., Jararweh, Y., Gupta, B., 2018. Deep Recurrent neural network vs. support vector machine for aspect-based sentiment analysis of Arabic hotels’ reviews. J. Comput. Sci. 27, 386–393. https://doi.org/10.1016/j.jocs.2017.11.006
  • Chiong, R., Fan, Z., Hu, Z., Adam, M.T.P., Lutz, B., Neumann, D., 2018. A Sentiment Analysis-based Machine Learning Approach for Financial Market Prediction via News Disclosures, in: Proceedings of the Genetic and Evolutionary Computation Conference Companion, GECCO ’18. ACM, New York, NY, USA, pp. 278–279. https://doi.org/10.1145/3205651.3205682
  • Sohangir, S., Wang, D., Pomeranets, A., Khoshgoftaar, T.M., 2018. Big Data: Deep Learning for financial sentiment analysis. J. Big Data 5, 3. https://doi.org/10.1186/s40537-017-0111-6
  • Demirtas, E., Pechenizkiy, M., 2013. Cross-lingual Polarity Detection with Machine Translation, in: Proceedings of the Second International Workshop on Issues of Sentiment Discovery and Opinion Mining, WISDOM ’13. ACM, New York, NY, USA, pp. 9:1–9:8. https://doi.org/10.1145/2502069.2502078
  • Baziotis, C., Pelekis, N., Doulkeridis, C., 2017. DataStories at SemEval-2017 Task 4: Deep LSTM with Attention for Message-level and Topic-based Sentiment Analysis, in: Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017). Association for Computational Linguistics, Vancouver, Canada, pp. 747–754.
  • González, J.-Á., Pla, F., Hurtado, L.-F., 2017. ELiRF-UPV at SemEval-2017 Task 4: Sentiment Analysis using Deep Learning, in: Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017). Association for Computational Linguistics, Vancouver, Canada, pp. 723–727.
  • Xia, R., Zong, C., Li, S., 2011. Ensemble of feature sets and classification algorithms for sentiment classification. Inf. Sci. 181, 1138–1152. https://doi.org/10.1016/j.ins.2010.11.023
  • Neethu, M.S., Rajasree, R., 2013. Sentiment analysis in twitter using machine learning techniques, in: 2013 Fourth International Conference on Computing, Communications and Networking Technologies (ICCCNT). Presented at the 2013 Fourth International Conference on Computing, Communications and Networking Technologies (ICCCNT), pp. 1–5. https://doi.org/10.1109/ICCCNT.2013.6726818
  • Fersini, E., Messina, E., Pozzi, F.A., 2014. Sentiment analysis: Bayesian Ensemble Learning. Decis. Support Syst. 68, 26–38. https://doi.org/10.1016/j.dss.2014.10.004
  • da Silva, N.F.F., Hruschka, Eduardo R., Hruschka, Estevam R., 2014. Tweet sentiment analysis with classifier ensembles. Decis. Support Syst. 66, 170–179. https://doi.org/10.1016/j.dss.2014.07.003
  • Catal, C., Nangir, M., 2017. A sentiment classification model based on multiple classifiers. Appl. Soft Comput. 50, 135–141. https://doi.org/10.1016/j.asoc.2016.11.022
  • Ankit, Saleena, N., 2018. An Ensemble Classification System for Twitter Sentiment Analysis. Procedia Comput. Sci., International Conference on Computational Intelligence and Data Science 132, 937–946. https://doi.org/10.1016/j.procs.2018.05.109
  • Araque, O., Corcuera-Platas, I., Sánchez-Rada, J.F., Iglesias, C.A., 2017. Enhancing deep learning sentiment analysis with ensemble techniques in social applications. Expert Syst. Appl. 77, 236–246. https://doi.org/10.1016/j.eswa.2017.02.002
  • Dedhia, C., Ramteke, J., 2017. Ensemble model for Twitter sentiment analysis, in: 2017 International Conference on Inventive Systems and Control (ICISC). Presented at the 2017 International Conference on Inventive Systems and Control (ICISC), pp. 1–5. https://doi.org/10.1109/ICISC.2017.8068711
  • Cliche, M., 2017. BB_twtr at SemEval-2017 Task 4: Twitter Sentiment Analysis with CNNs and LSTMs. ArXiv170406125 Cs Stat.
  • Tan, S., Zhang, J., 2008. An empirical study of sentiment analysis for chinese documents. Expert Syst. Appl. 34, 2622–2629. https://doi.org/10.1016/j.eswa.2007.05.028
  • Go, A., Huang, L., Bhayani, R., 2009b. Twitter Sentiment Analysis.
  • Meral, M., Diri, B., 2014. Sentiment analysis on Twitter, in: 2014 22nd Signal Processing and Communications Applications Conference (SIU). Presented at the 2014 22nd Signal Processing and Communications Applications Conference (SIU), pp. 690–693. https://doi.org/10.1109/SIU.2014.6830323
  • Vinodhini, G., Chandrasekaran, R., n.d. Effect of Feature Reduction in Sentiment analysis of online reviews. IJARCET 2, 9.
  • Yousefpour, A., Ibrahim, R., Abdull Hamed, H.N., 2014. A Novel Feature Reduction Method in Sentiment Analysis. Int. J. Innov. Comput. 4.
  • Kim, K., Lee, J., 2014. Sentiment visualization and classification via semi-supervised nonlinear dimensionality reduction. Pattern Recognit. 47, 758–768. https://doi.org/10.1016/j.patcog.2013.07.022
  • Kim, K., 2018. An improved semi-supervised dimensionality reduction using feature weighting: Application to sentiment analysis. Expert Syst. Appl. 109, 49–65. https://doi.org/10.1016/j.eswa.2018.05.023
  • Vapnik, V., 2013. The Nature of Statistical Learning Theory. Springer Science & Business Media.
  • Wright, R.E., 1995. Logistic regression, in: Reading and Understanding Multivariate Statistics. American Psychological Association, Washington, DC, US, pp. 217–244.
  • Dayhoff, J.E., DeLeo, J.M., 2001. Artificial neural networks. Cancer 91, 1615–1635. https://doi.org/10.1002/1097-0142(20010415)91:8+1615::AID-CNCR11753.0.CO;2-L
  • Lowd, D., Domingos, P., 2005. Naive Bayes Models for Probability Estimation, in: Proceedings of the 22Nd International Conference on Machine Learning, ICML ’05. ACM, New York, NY, USA, pp. 529–536. https://doi.org/10.1145/1102351.1102418
  • Pal, M., 2005. Random forest classifier for remote sensing classification. Int. J. Remote Sens. 26, 217–222. https://doi.org/10.1080/01431160412331269698
  • Larose, D.T., 2004. k-Nearest Neighbor Algorithm, in: Discovering Knowledge in Data. John Wiley & Sons, Inc., pp. 90–106. https://doi.org/10.1002/0471687545.ch5
  • Chen, Y., Chen, F., Yang, J.Y., Yang, M.Q., 2008. Ensemble voting system for multiclass protein fold recognition. Int. J. Pattern Recognit. Artif. Intell. 22, 747–763. https://doi.org/10.1142/S0218001408006454
  • Chen, Y., Wong, M.L., 2011. Optimizing Stacking Ensemble by an Ant Colony Optimization Approach, in: Proceedings of the 13th Annual Conference Companion on Genetic and Evolutionary Computation, GECCO ’11. ACM, New York, NY, USA, pp. 7–8. https://doi.org/10.1145/2001858.2001863
  • Sentiment classification on Large Movie Review [WWW Document], 2018. URL https://www.kaggle.com/c/sentiment-classification-on-large-movie-review/data
  • Rosenthal, S., Farra, N., Nakov, P., 2017. SemEval-2017 Task 4: Sentiment Analysis in Twitter, in: Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017). Association for Computational Linguistics, Vancouver, Canada, pp. 502–518.
  • Salton, G., Buckley, C., 1988. Term-weighting approaches in automatic text retrieval. Inf. Process. Manag. 24, 513–523. https://doi.org/10.1016/0306-4573(88)90021-0
  • Aizawa, A., 2003. An information-theoretic perspective of tf–idf measures. Inf. Process. Manag. 39, 45–65. https://doi.org/10.1016/S0306-4573(02)00021-3
  • Mikolov, T., Chen, K., Corrado, G., Dean, J., 2013a. Efficient Estimation of Word Representations in Vector Space.
  • Tillmann, C., 2004. A Unigram Orientation Model for Statistical Machine Translation, in: Proceedings of HLT-NAACL 2004: Short Papers, HLT-NAACL-Short ’04. Association for Computational Linguistics, Stroudsburg, PA, USA, pp. 101–104.
  • Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J., 2013b. Distributed Representations of Words and Phrases and their Compositionality, in: Burges, C.J.C., Bottou, L., Welling, M., Ghahramani, Z., Weinberger, K.Q. (Eds.), Advances in Neural Information Processing Systems 26. Curran Associates, Inc., pp. 3111–3119.
  • Goodman, J., 2001. Classes for fast maximum entropy training, in: 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221). Presented at the 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221), pp. 561–564 vol.1. https://doi.org/10.1109/ICASSP.2001.940893
  • Görmez, Y., 2017. Dimensionality reduction for protein secondary structure prediction. Abdullah Gül Üniversitesi, YÖK.
  • Supervise Learning [WWW Document], 2018. URL http://scikit-learn.org/stable/supervised_learning.html#supervised-learning
  • Stacking Classifier [WWW Document], 2018. URL https://rasbt.github.io/mlxtend/user_guide/classifier/StackingClassifier/
  • Keras: The Python Deep Learning library [WWW Document], 2018. URL https://keras.io/
  • Precision and recall [WWW Document], 2017. URL https://en.wikipedia.org/wiki/Precision_and_recall
  • Z Score Calculator for 2 Population Proportions [WWW Document], 2018. URL https://www.socscistatistics.com/tests/ztest/Default2.aspx
Еще
Статья научная