Enhanced Sentiment Classification for Dual Sentiment Analysis using BiLSTM and Convolution Neural Network Classifier

Enhanced Sentiment Classification for Dual Sentiment Analysis using BiLSTM and Convolution Neural Network Classifier
  IJETT-book-cover           
  
© 2022 by IJETT Journal
Volume-70 Issue-1
Year of Publication : 2022
Authors : Mamatha M, Rakshith Shenoy, Thriveni J, Venugopal K R
DOI :  10.14445/22315381/IJETT-V70I1P217

How to Cite?

Mamatha M, Rakshith Shenoy, Thriveni J, Venugopal K R, "Enhanced Sentiment Classification for Dual Sentiment Analysis using BiLSTM and Convolution Neural Network Classifier," International Journal of Engineering Trends and Technology, vol. 70, no. 3, pp. 151-161, 2022. Crossref, https://doi.org/10.14445/22315381/IJETT-V70I1P217

Abstract
Sentiment Classification is one of the fundamental tasks in sentiment analysis that aims to classify the orientation of a given text (e.g., positive or negative). Analysis of sentiment in the text provides an advantage for customers in services and analysis. The text classification in sentiment analysis is performed using Bag-of-words(BOW) model, which is a machine learning approach. Dual Sentiment analysis(DSA) with BiLSTM and CNN is used to address the polarity shift problem that arises in classification. These classifiers perform sequence prediction and provide better results when compared to other methods. Initially, a data expansion technique is proposed that makes use of opposite labels of positive and negative sentiment for each training and test review sentence. Next, in dual training, the probabilities of original and reverse reviews are trained on the classifier. Predictions in dual prediction are done by considering two sides of one review. As the work is carried over on text reviews, the lexicon-based dictionary is used. The proposed model is evaluated on four multi-domain datasets. As compared to SVM and other classifiers, our methods give better results.

Keywords
Bag-of-words, BiLSTM, Dual Sentiment Analysis, Machine Learning, Neural Networks, Sequence Prediction

Reference
[1] S. Zirpe and B. Joglekar, Polarity Shift Detection approaches in Sentiment Analysis: A Survey, International Conference on Inventive Systems and Control(ICISC), (2017) 1–5.
[2] R. Xia, F. Xu, J. Yu, Y. Qi, and E. Cambria, Polarity Shift Detection, Elimination and Ensemble: A Three-stage Model for Document-Level Sentiment Analysis, International Journal on Information Processing and Management, 52 (2016) 36–45.
[3] A. Jangde and P. Malviya, Opinion Analysis Using Polarity Shift Model, International Journal of Computing and Technology, 10 (2017) 1–309.
[4] Y. Goldberg, Neural Networks method for Natural Language Processing, Synthesis Lectures on Human Language Technologies, 4 (2017) 34–38.
[5] L. Shoushan and C.-R. Huang, Sentiment Classification Considering Negation and Contrast Transition, 23rd Pacific Asia Conference on Language, Information and Computation, (2010) 297–306.
[6] T. Wilson, J. Wiebe, and P. Hoffmann, Recognizing Contextual Polarity: An Exploration of Features for Phrase-Level Sentiment Analysis, Association for Computation Linguistics, 35 (2009) 399– 433.
[7] L. Shoushan, S. Y. Mei Lee, Y. Chen, C.-R. Huang, and G. Zhou, Sentiment Classification and Polarity Shifting, Proceedings of the 23rd International Conference on Computational Linguistics, (2010) 635–643.
[8] B. Pang, L. Lee, and S. Vaithyanathan, Thumbs Up? Sentiment Classification using Machine Learning Techniques, Proceedings of the 2002 Conference on Empirical Methods in Natural Language Processing, (2002) 79–86.
[9] S. Das and M. Chen, Yahoo! for Amazon: Extracting Market Sentiment from Stock Message Boards, Asia Pacific Finance Association Annual Conference(APFA), (2001) 79–86.
[10] R. Xia, F. Xu, C. Zong, Q. Li, Y. Qi, and T. Li, Dual Sentiment Analysis: Considering Two Sides of One Review, IEEE Transactions on Knowledge and Data Engineering, 27 (2015) 2120- 2133.
[11] M. V. Mantyla, D. Graziotin, and M. Kuutila, The Evolution of Sentiment Analysis - A Review of Research Topics, Venues, and Top Cited Papers, Computer Science Review, 27 (2018) 16–32.
[12] B. Pang and L. Lee, Opinion Mining and Sentiment Analysis, Foundations and Trends in Information Retrie 2 (2008) 1–135.
[13] R. Prabow and M. Thelwall, Sentiment Analysis: A Combined Approach, International Journal of Informetrics, 3 (2009) 143–157.
[14] Y. Choi and C. Cardie, “Learning with Compositional Semantics as Structural Inference for Subsentential Sentiment Analysis,” Proceedings of the Conference on Empirical Methods in Natural Language Processing(EMNLP), (2008) 793–801.
[15] R. Xia, T. Wang, X. Hu, S. Li, and C. Zong, Dual Training and Dual Prediction for Polarity Classification, Association for Computation Linguistics, (2013).
[16] H. Deshmukh and P. L. Ramteke, An Overview of Sentiment Analysis Model for Polarity Classification by User Perspective Review, Inter- national Journal of Advanced Research in Computer Engineering and Technology (IJARCET), 6 (2017) 77–79.
[17] P. K. Manna and S. Bodkhe, Three-Stage Sentiment Analysis by Polarity Shift Detection, Elimination and Ensemble, International Journal of Advanced Computational Engineering and Networking, 3 (2015) 58–61.
[18] P. D. Turney, Thumbs Up or Thumbs Down? Semantic Orientation Applied to Unsupervised Classification of Reviews, Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, (2002) 417–424.
[19] M. Taboada, J. Brooke, M. Tofiloski, K. Voll, and M. Stede, Lexicon- Based Methods for Sentiment Analysis, Association for Computational Linguistics, 37 (2011) 267–307.
[20] A. M. Ramadhani and H. S. Goo, Twitter Sentiment Analysis using Deep Learning Methods, International Annual Engineering Seminar, (2017) 1–4.
[21] H. Lakkaraju, R. Socher, and M. Chris, Aspect Specific Sentiment Analysis using Hierarchical Deep Learning, (2014) 1–9.
[22] D. Tang, B. Qin, X. Feng, and T. Liu, Effective LSTMs for Target- Dependent Sentiment Classification, Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, (2016) 3298–3307.
[23] D. Li, F. Wei, C. Tan, D. Tang, M. Zhou, and K. Xu, Adaptive Recursive Neural Network for Target-dependent Twitter Sentiment Classification, Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, (2014) 49–54.
[24] X. Wang, W. Jiang, and Z. Luo, Combination of Convolutional and Recurrent Neural Network for Sentiment Analysis of Short Texts, Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, (2016) 242–243.
[25] Y. Kim, Convolutional Neural Networks for Sentence Classification, Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), (2014).
[26] T. Mikolov, K. Chen, G. S. Corrado, and J. Dean, Efficient Estimation of Word Representations in Vector Space, International Conference on Learning Representations, (2013) 1–12.
[27] T. Mikolov, I. Sutskever, K. Chen, G. S. Corrado, and J. Dean, Distributed Representations of Words and Phrases and their Compositionality, Proceedings of the 26th International Conference on Neural Information Processing Systems, 2 (2013) 1–12.
[28] S. Rida-E-Fatima, A. Javed, A. Banjar, A. Irtaza, H. Dawood, H. Da- wood, and A. Alamri, A Multi-Layer Dual Attention Deep Learning Model with Refined Word Embeddings for Aspect-Based Sentiment Analysis, IEEE Access, 7 (2019) 114 795–114 807.