An Aspect based Multi‑label Sentiment Analysis using Improved BERT System

Authors

  • Sofiya S. Mujawar Phd scholar, Department of Computer science and Engineering, Sandip University, Nashik
  • Pawan R. Bhaladhare Professor, Department of Computer science and Engineering, Sandip University, Nashik

Keywords:

Aspect Based Sentiment Analysis (ABSA), Text classification, multilabel classifier, Dimensionality reduction, Bidirectional Encode Representation from Transformers (BERT), Artificial Intelligence

Abstract

Digital interaction has become more prevalent as a result of the increasing development of social Media and Web, making the customer active players. Customers' reviews uploaded on the Internet today provide crucial data towards other clients due to the vast quantity of reviews provided by consumers today. Since this type of information is extremely important for decision-making, it is extremely popular among internet users. Because of this, an automation system to analyses and retrieve insight from textual data is required. Sentiment classification is a well-known sub-area of Artificial Intelligence and Natural Language Processing that studies how people feel (NLP). The sentiments of participants in previous studies were calculated without taking into account the aspects indicated in a reviewing instances. In recent years, scholars have become interested in aspect-based sentiment analysis (ABSA). Numerous existing systems treat ABSA as if it were a single-label classification problem. This issue is addressed in this paper by presenting ways that make use of multilabeling classifiers for classification, which overcomes the problem. So rather than single label classifiers, the suggested approach employs the upgraded BERT system just for word embedding, with classification performed using multilabeling classifiers rather than single label classifiers. According to all methodologies, the label that is utilised for all learning classifiers identifies aspects by expressing their emotions. In this technique, the findings achieved via experimentation show that they are superior to the findings acquired through other existing researches when employing the system provided in this approach.

Downloads

Download data is not yet available.

References

Deng, S., Sinha, A.P., Zhao, H. (2017). Adapting sentiment lexicons to domain-specific social media texts. Decision Support Systems, 94: 65-76. https://doi.org/10.1016/j.dss.2016.11.001

Lee, G., Jeong, J., Seo, S., Kim, C.Y., Kang, P. (2018). Sentiment classification with word localization based on weakly supervised learning with a convolutional neural network. Knowledge-Based Systems, 152: 70-82. https://doi.org/10.1016/j.knosys.2018.04.006

Tao, J., Zhou, L., Feeney, C. (2019). I understand what you are saying: leveraging deep learning techniques for aspect based sentiment analysis. Proceedings of the 52nd Hawaii International Conference on System Sciences. https://doi.org/10.24251/HICSS.2019.057

Rida-E-Fatima, S., Javed, A., Banjar, A., Irtaza, A., Dawood, H., Dawood, H., Alamri, A. (2019). A multi-layer dual attention deep learning model with refined word embeddings for aspect-based sentiment analysis. IEEE Access, 7: 114795-114807. https://doi.org/10.1109/ACCESS.2019.2927281

Yu, L.C., Wang, J., Lai, K.R., Zhang, X. (2017). Refining word embeddings using intensity scores for sentiment analysis. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 26(3): 671-681. https://doi.org/10.1109/TASLP.2017.2788182

Tang, D., Qin, B., Feng, X., Liu, T. (2016). Effective LSTMs for target-dependent sentiment classification. Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical, pp. 3298-3307.

Meng, W., Wei, Y., Liu, P., Zhu, Z., Yin, H. (2019). Aspect based sentiment analysis with feature enhanced attention CNN-BiLSTM. IEEE Access, 7: 167240-167249. https://doi.org/10.1109/ACCESS.2019.2952888

Liu, G., Guo, J. (2019). Bidirectional LSTM with attention mechanism and convolutional layer for text classification. Neurocomputing, 337: 325-338. https://doi.org/10.1016/j.neucom.2019.01.078

Ishaq, A., Asghar, S., Gillani, S.A. (2020). Aspect-based sentiment analysis using a hybridized approach based on CNN and GA. IEEE Access, 8: 135499-135512. https://doi.org/10.1109/ACCESS.2020.3011802

Akhtar, M.S., Gupta, D., Ekbal, A., Bhattacharyya, P. (2017). Feature selection and ensemble construction: A two-step method for aspect based sentiment analysis. Knowledge-Based Systems, 125: 116-135. https://doi.org/10.1016/j.knosys.2017.03.020

Pham, D.H., Le, A.C. (2018). Learning multiple layers of knowledge representation for aspect based sentiment analysis. Data & Knowledge Engineering, 114: 26-39. https://doi.org/10.1016/j.datak.2017.06.001

Liu, S.M., Chen, J.H. (2015). A multi-label classification based approach for sentiment classification. Expert Systems with Applications, 42(3): 1083-1093. https://doi.org/10.1016/j.eswa.2014.08.036

Cai, L., Song, Y., Liu, T., Zhang, K. (2020). A hybrid BERT model that incorporates label semantics via adjustive attention for multi-label text classification. IEEE Access, 8: 152183-152192. https://doi.org/10.1109/ACCESS.2020.3017382

Li, X., Fu, X., Xu, G., Yang, Y., Wang, J., Jin, L., Liu, Q., Xiang, T. (2020). Enhancing BERT representation with context-aware embedding for aspect-based sentiment analysis. IEEE Access, 8: 46868-46876. https://doi.org/10.1109/ACCESS.2020.2978511

Kang, Y., Zhou, L. (2017). RubE: Rule-based methods for extracting product features from online consumer reviews. Information & Management, 54(2): 166-176. https://doi.org/10.1016/j.im.2016.05.007

Liu, N., Shen, B., Zhang, Z., Zhang, Z., Mi, K. (2019). Attention-based sentiment reasoner for aspect-based sentiment analysis. Human-centric Computing and Information Sciences, 9(1): 1-17. https://doi.org/10.1186/s13673-019-0196-3

He, Y., Lin, C., Alani, H.: Automatically Extracting Polarity-bearing Topics for Cross-domain Sentiment Classification. In: Proceedings 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, pp. 19–24, Portland (2011)

Hu, M., Liu, B.: Mining and Summarizing Customer Reviews. In: Proceedings of the tenth ACM SIGKDD international conference on Knowledge Discovery and Data Mining (168–177). ACM (2004)

Liu, C.L., Hsaio, W.H., Lee, C.H., Lu, G.C., Jou, E.: Movie rating and review summarization in mobile environment, Systems, Man and cybernetics, Part C: Applications and reviews. IEEE Trans., 397–407 (2012)

Pontiki M, Galanis D, Pavlopoulos J, Papageorgiou H, Androutsopoulos I, Manandhar S. (2014). SemEval-2014 Task 4: Aspect Based Sentiment Analysis. Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014) (Association for Computational Linguistics) 27-35.

Bhamare, B.R., Prabhu, J. (2021). A multilabel classifier for text classification and enhanced BERT system. Revue d'Intelligence Artificielle, Vol. 35, No. 2, pp. 167-176. https://doi.org/10.18280/ria.350209

Proposed Architecture for Improved BERT Mechanism

Downloads

Published

14.01.2023

How to Cite

[1]
S. S. . Mujawar and P. R. . Bhaladhare, “An Aspect based Multi‑label Sentiment Analysis using Improved BERT System ”, Int J Intell Syst Appl Eng, vol. 11, no. 1s, pp. 228–235, Jan. 2023.