Unifying Adversarial Adaptation and Maximum Mean Discrepancy for Enhanced Cross-Domain Aspect Sentiment Classification
Keywords:
Cross-Domain Aspect based Sentiment Analysis, Aspect Extraction, Sentiment Classification, Adversarial Domain Adaptation, Maximum Mean DiscrepancyAbstract
Cross-domain sentiment analysis is a fundamental challenge in NLP with applications in diverse areas such as product reviews, customer feedback, and social media monitoring. In this paper, we propose a comprehensive approach for Cross-Domain Aspect-Based Sentiment Analysis (CD-ABSA) that integrates aspect extraction and sentiment classification. Leveraging pre-trained Bidirectional Encoder Representations from Transformers (BERT) models, our methodology presents a novel framework that utilizes Adversarial Domain Adaptation, incorporating Maximum Mean Discrepancy (MMD) to facilitate the adaptation of sentiment classifiers from one domain to another, specifically in the restaurants, laptops, books, and clothes domains. Our approach ensures accurate sentiment analysis across diverse domains by reducing the distribution gap through adversarial domain adaptation and MMD(ADA-MMD). We evaluate our model using accuracy and F1-Scores and show its superior performance compared to existing methods. This research represents a significant step towards domain-agnostic sentiment analysis by combining aspect extraction and sentiment classification within a unified framework, providing practical solutions for scenarios with limited or no domain-specific labeled data.
Downloads
References
Wankhade, M., Rao, A.C.S. & Kulkarni, C. A survey on sentiment analysis methods, applications, and challenges. Artif Intell Rev 55, 5731–5780 (2022).
Sampathirao Suneetha, Prof. S. Viziananda Row, “ Aspect-Based Sentiment Analysis: A Comprehensive Survey of Techniques and Applications”, Journal of Data Acquisition and Processing, 2023, 38 (3): 177-203.
A. Nazir, Y. Rao, L. Wu and L. Sun, "Issues and Challenges of Aspect-based Sentiment Analysis: A Comprehensive Survey," in IEEE Transactions on Affective Computing, vol. 13, no. 2, pp. 845-863, 1 April-June 2022, doi: 10.1109/TAFFC.2020.2970399.
B. Zhang, X. Fu, C. Luo, Y. Ye, X. Li and L. Jing, "Cross-Domain Aspect-based Sentiment Classification by Exploiting Domain-Invariant Semantic-primary Feature," in IEEE Transactions on Affective Computing, doi: 10.1109/TAFFC.2023.3239540.
Sampathirao Suneetha and Prof. S. Viziananda Row, (2023). Cross-Domain Aspect Extraction using Adversarial Domain Adaptation. International Journal on Recent and Innovation Trends in Computing and Communication, 11(11s), 672–682. Retrieved from https://ijritcc.org/index.php/ijritcc/article/view/9658.
Devlin, Jacob, Ming-Wei Chang, Kenton Lee and Kristina Toutanova. “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.” North American Chapter of the Association for Computational Linguistics (2019).
W. Wang et al., "Rethinking Maximum Mean Discrepancy for Visual Domain Adaptation," in IEEE Transactions on Neural Networks and Learning Systems, vol. 34, no. 1, pp. 264-277, Jan. 2023, doi: 10.1109/TNNLS.2021.3093468.
Paik, Seunghoon & Celentano, Michael & Green, Alden & Tibshirani, Ryan. (2023). Maximum Mean Discrepancy Meets Neural Networks: The Radon-Kolmogorov-Smirnov Test. arXiv:2309.02422v3.
HassanPour Zonoozi, M., Seydi, V. A Survey on Adversarial Domain Adaptation. Neural Process Lett 55, 2429–2469 (2023). https://doi.org/10.1007/s11063-022-10977-5
Mitchell, Margaret, Jacqui Aguilar, Theresa Wilson, and Benjamin Van Durme. 2013.“Open Domain Targeted Sentiment.” In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, 1643–54.
Zhang, Lei, Shuai Wang, and Bing Liu. 2018.“Deep Learning for Sentiment Analysis: A Survey.” Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery 8 (4): e1253.
Li, Xin, Lidong Bing, Wai Lam, and Bei Shi. 2019a.“Transformation Networks for Target-Oriented Sentiment Classification.” In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 946–56.
He, Ruidan, Wee Sun Lee, Hwee Tou Ng, and Daniel Dahlmeier. 2019.“Interactive Multi-Task Learning Network for End-to-End Aspect-Based Sentiment Analysis.” In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 5966–75.
Zhou, Hao, Zhenting Yu, Yue Zhang, Shujian Huang, XIN-YU DAI, and Jiajun Chen. 2019.“Syntax-Aware Aspect Level Sentiment Classification with Graph Attention Networks.” In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), 3534–43.
Li, Xin, Lidong Bing, Piji Li, Wai Lam, and Zhimou Yang. 2017.“Aspect Term Extraction with History Attention and Selective Transformation.” In Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI-17), 4194–200.
He, Ruidan, Wee Sun Lee, Hwee Tou Ng, and Daniel Dahlmeier. 2018.“Effective Attention Modeling for Aspect-Level Sentiment Classification.” In Proceedings of the 27th International Conference on Computational Linguistics (COLING), 1122–32.
Li,Xin,Lidong Bing, Wai Lam, and Bei Shi. 2018.“A Unified Model for Opinion Target Extraction and Target Sentiment Prediction.” In Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18), 6714–21.
Zhang, Lei, Shuai Wang, and Bing Liu. 2019.“Aspect and Opinion Terms Co-Extraction Based on Partially-Supervised Word Alignment Model.” IEEE Transactions on KDE 31 (2): 353–66.
Jakob, Niklas, and Iryna Gurevych. 2010.“Extracting Opinion Targets in a Single-and Cross-Domain Setting with Conditional Random Fields.” In Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing, 1035–45.
Li, Fangtao, Minlie Huang, Xiaoyan Zhu, and Ji Wu. 2012.“Learning to Identify Review Spam.” In Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence (IJCAI-11), 2488–94.
Ding, Xiaowen, Bing Liu, and Philip S. Yu. 2017.“A Holistic Lexicon-Based Approach to Opinion Mining.” In Proceedings of the 2008 International Conference on Web Search and Data Mining (WSDM), 231–40.
Wang, Wenya, and Sinno Jialin Pan. 2018.“Recursive Neural Networks with Multi-Domain Adaptation for Aspect and Opinion Term Co-Extraction.” In Proceedings of the 27th International Conference on Computational Linguistics (COLING), 3516–26.
Chenggong Gong, Jianfei Yu, and Rui Xia. 2020. Unified feature and instance based domain adaptation for aspect-based sentiment analysis. In Proceedings of EMNLP, pages 7035–7045.
Xiang Chen and Xiaojun Wan. 2022. A simple information-based approach to unsupervised domain adaptive aspect-based sentiment analysis. arXiv preprint arXiv:2201.12549.
Yu, Chenggong Gong, and Rui Xia. 2021. Cross domain review generation for aspect-based sentiment analysis. In Findings of the Association for Computational Linguistics: ACL/IJCNLP 2021, pages 4767–4777.
Yu, Jianfei, Qiankun Zhao and Rui Xia. “Cross-Domain Data Augmentation with Domain-Adaptive Language Modeling for Aspect-Based Sentiment Analysis.” Annual Meeting of the Association for Computational Linguistics (2023).
Li,Xin,Lidong Bing, Wai Lam, and Zhimou Yang. 2019. “Cross-Domain Aspect-Based Sentiment Analysis with Selective Adversarial Learning.” In Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence (IJCAI-19), 5271–77.
Tabassum, Ayisha and Dr. Rajendra R. Patil. “A Survey on Text Pre-Processing & Feature Extraction Techniques in Natural Language Processing.” IRJET (2020).
S. Albawi, T. A. Mohammed and S. Al-Zawi, "Understanding of a convolutional neural network," 2017 International Conference on Engineering and Technology (ICET), Antalya, Turkey, 2017, pp. 1-6, doi: 10.1109/ICEngTechnol.2017.8308186.
Kiprono Elijah Koech, " Cross-Entropy Loss Function", Published in Towards Data Science, Oct 2, 2020.
K. Osumi, T. Yamashita and H. Fujiyoshi, "Domain Adaptation using a Gradient Reversal Layer with Instance Weighting," 2019 16th International Conference on Machine Vision Applications (MVA), Tokyo, Japan, 2019, pp. 1-5, doi: 10.23919/MVA.2019.8757975.
Gretton A, Borgwardt KM, Rasch MJ, Schölkopf B, Smola A (2012) A kernel two-sample test. J Mach Learn Res 13(Mar):723–773.
Maria Pontiki, Dimitris Galanis, John Pavlopoulos, Harris Papageorgiou, Ion Androutsopoulos, and Suresh Manandhar. 2014. SemEval-2014 Task 4: Aspect Based Sentiment Analysis. In Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014), pages 27–35, Dublin, Ireland. Association for Computational Linguistics.
Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pierric Cistac, Tim Rault, Remi Louf, Morgan Funtowicz, Joe Davison, Sam Shleifer, Patrick von Platen, Clara Ma, Yacine Jernite, Julien Plu, Canwen Xu, Teven Le Scao, Sylvain Gugger, et al. 2020. Transformers: State-of-the-Art Natural Language Processing. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 38–45, Online. Association for Computational Linguistics.
Loshchilov and F. Hutter. 2019. Decoupled Weight Decay Regularization. In ICLR.
Jacob Devlin Ming-Wei Chang Kenton and Lee Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of NAACL-HLT, pages 4171–4186.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
