ABSTRACT
The Aspect-Based Sentiment Classification (ABSC) models often suffer from a lack of training data in some domains. To exploit the abundant data from another domain, this work extends the original state-of-the-art LCR-Rot-hop++ model that uses a neural network with a rotatory attention mechanism for a cross-domain setting. More specifically, we propose a Domain-Independent Word Selector (DIWS) model that is used in combination with the LCR-Rot-hop++ model (DIWS-LCR-Rot-hop++). It uses attention weights from the domain classification task to determine whether a word is domain-specific or domain-independent, and discards domain-specific words when training and testing the LCR-Rot-hop++ model for cross-domain ABSC. Overall, our results confirm that DIWS-LCR-Rot-hop++ outperforms the original LCR-Rot-hop++ model under a cross-domain setting in case we impose a domain-dependent threshold value for deciding whether a word is domain-specific or not. For a target domain that is highly similar to the source domain, we find that a moderate attention threshold yields the best performance, while a target domain that is dissimilar requires a high attention threshold. Also, we observe information loss when we impose a too strict restriction and classify a small proportion of words as domain-independent.
- Gianni Brauwers and Flavius Frasincar. 2022. A Survey on Aspect-Based Sentiment Classification. Comput. Surveys (2022). Google ScholarDigital Library
- Xilun Chen and Claire Cardie. 2018. Multinomial Adversarial Networks for Multi-Domain Text Classification. In 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT 2018). ACL, 1226--1240.Google Scholar
- Li Dong, Furu Wei, Chuanqi Tan, Duyu Tang, Ming Zhou, and Ke Xu. 2014. Adaptive recursive neural network for target-dependent Twitter sentiment classification. In 52nd Annual Meeting of the Association for Computational Linguistics (ACL 2014). ACL, 49--54.Google ScholarCross Ref
- Yaroslav Ganin, Evgeniya Ustinova, Hana Ajakan, Pascal Germain, Hugo Larochelle, François Laviolette, Mario Marchand, and Victor S. Lempitsky. 2017. Domain-Adversarial Training of Neural Networks. In Domain Adaptation in Computer Vision Applications. Springer, 189--209.Google Scholar
- Alex Graves and Jürgen Schmidhuber. 2005. Framewise phoneme classification with bidirectional LSTM and other neural network architectures. Neural Networks 18, 5-6 (2005), 602--610.Google ScholarDigital Library
- Jiang Guo, Darsh J. Shah, and Regina Barzilay. 2018. Multi-Source Domain Adaptation with Mixture of Experts. In 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP 2018). ACL, 4694--4703.Google Scholar
- Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long Short-Term Memory. Neural Computation 9, 8 (1997), 1735--1780.Google ScholarDigital Library
- Minqing Hu and Bing Liu. 2004. Mining and summarizing customer reviews. In 10th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2004). ACM, 168--177.Google ScholarDigital Library
- Joris Knoester, Flavius Frasincar, and Maria Truşcă. 2022. Domain Adversarial Training for Aspect-Based Sentiment Analysis. In 23rd International Conference on Web Information Systems (WISE 2022) (LNCS). Springer.Google Scholar
- Zheng Li, Ying Wei, Yu Zhang, and Qiang Yang. 2018. Hierarchical Attention Transfer Network for Cross-Domain Sentiment Classification. In 32nd AAAI Conference on Artificial Intelligence (AAAI 2018). AAAI Press, 5852--5859.Google Scholar
- Bing Liu. 2020. Sentiment Analysis - Mining Opinions, Sentiments, and Emotions (second ed.). Cambridge University Press.Google Scholar
- Stephan Oepen, Marco Kuhlmann, Yusuke Miyao, Daniel Zeman, Silvie Cinková, Dan Flickinger, Jan Hajič, and Zdeňka Urešová. 2015. SemEval 2015 Task 18: Broad-Coverage Semantic Dependency Parsing. In 9th International Workshop on Semantic Evaluation (SemEval 2015). ACL, 915--926.Google Scholar
- Maria Pontiki, Dimitris Galanis, John Pavlopoulos, Harris Papageorgiou, Ion Androutsopoulos, and Suresh Manandhar. 2014. SemEval-2014 Task 4: Aspect Based Sentiment Analysis. In 8th International Workshop on Semantic Evaluation (SemEval 2014). ACL, 27--35.Google ScholarCross Ref
- Sebastian Ruder, Parsa Ghaffari, and John G. Breslin. 2016. A Hierarchical Model of Reviews for Aspect-based Sentiment Analysis. In 2016 Conference on Empirical Methods in Natural Language Processing (EMNLP 2016). ACL, 999--1005.Google ScholarCross Ref
- Xiaobing Sun and Wei Lu. 2020. Understanding Attention for Text Classification. In 58th Annual Meeting of the Association for Computational Linguistics, (ACL 2020). ACL, 3418--3428.Google Scholar
- Maria Mihaela Truşcâ, Daan Wassenberg, Flavius Frasincar, and Rommert Dekker. 2020. A hybrid approach for aspect-based sentiment analysis using deep contextual word embeddings and hierarchical attention. In 20th International Conference of Web Engineering (ICWE 2020) (LNCS), Vol. 12128. Springer, 365--380.Google Scholar
- Stefan van Berkum, Sophia van Megen, Max Savelkoul, Pim Weterman, and Flavius Frasincar. 2021. Fine-Tuning for Cross-Domain Aspect-Based Sentiment Classification. In 20th IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT 2021). ACM, 524--531.Google Scholar
- Olaf Wallaart and Flavius Frasincar. 2019. A Hybrid Approach for Aspect-Based Sentiment Analysis Using a Lexicalized Domain Ontology and Attentional Neural Models. In 16th Extended Sematic Web Conference (ESWC 2019) (LNCS), Vol. 11503. Springer, 363--378.Google ScholarCross Ref
- Jianhua Yuan, Yanyan Zhao, and Bing Qin. 2022. Learning to share by masking the non-shared for multi-domain sentiment classification. International Journal of Machine Learning and Cybernetics (2022), 1--14.Google ScholarCross Ref
- Meishan Zhang, Yue Zhang, and Duy-Tin Vo. 2016. Gated Neural Networks for Targeted Sentiment Analysis. In 30th AAAI Conference on Artificial Intelligence (AAAI 2016). AAAI Press, 3087--3093.Google Scholar
- Han Zhao, Shanghang Zhang, Guanhang Wu, José M. F. Moura, João Paulo Costeira, and Geoffrey J. Gordon. 2018. Adversarial Multiple Source Domain Adaptation. In 32nd International Conference on Neural Information Processing Systems (NIPS 2018). Curran Associates, 8568--8579.Google Scholar
- Renjie Zheng, Junkun Chen, and Xipeng Qiu. 2018. Same Representation, Different Attentions: Shareable Sentence Representation Learning from Multiple Tasks. In 27th International Joint Conference on Artificial Intelligence (IJCAI 2018). International Joint Conferences on Artificial Intelligence Organization, 4616--4622.Google ScholarCross Ref
- Shiliang Zheng and Rui Xia. 2018. Left-center-right separated neural network for aspect-based sentiment analysis with rotatory attention. arXiv preprint arXiv:1802.00892 (2018).Google Scholar
- Yftah Ziser and Roi Reichart. 2018. Pivot Based Language Modeling for Improved Neural Domain Adaptation. In 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT 2018). ACL, 1241--1251.Google Scholar
Index Terms
- A Cross-Domain Aspect-Based Sentiment Classification by Masking the Domain-Specific Words
Recommendations
DIWS-LCR-Rot-hop++: A Domain-Independent Word Selector for Cross-Domain Aspect-Based Sentiment Classification
The Aspect-Based Sentiment Classification (ABSC) models often suffer from a lack of training data in some domains. To exploit the abundant data from another domain, this work extends the original state-of-the-art LCR-Rot-hop++ model that uses a neural ...
An Enhanced Approach to Map Domain-Specific Words in Cross-Domain Sentiment Analysis
AbstractDomain adaptation in sentiment analysis is one of the areas where a classifier trained in one domain often classifies sentiments poorly when applied to another domain due to domain-specific words. Extracting features and their relevant opinion ...
Cross-domain sentiment classification via spectral feature alignment
WWW '10: Proceedings of the 19th international conference on World wide webSentiment classification aims to automatically predict sentiment polarity (e.g., positive or negative) of users publishing sentiment data (e.g., reviews, blogs). Although traditional classification algorithms can be used to train sentiment classifiers ...
Comments