Graph Convolutional Networks with Bidirectional Attention for Aspect-Based Sentiment Classification
Abstract
:1. Introduction
- We propose to adopt the syntactic dependency structure in sentences and solve the problem of long-distance multi-word dependence based on aspect-based sentiment classification;
- We design a bidirectional attention mechanism to enhance the interaction between aspect and context to obtain aspect specific context representation;
- Experiments on three benchmarking collections indicated that the effectiveness of our model compared with other popular models.
2. Related Work
3. Methodology
3.1. Embedding Layer
3.2. Attention Encoder Layer
3.2.1. Multi-Head Attention
3.2.2. Point-Wise Convolution Transformation
3.3. Position Encoding
3.4. GCN Module
3.5. Bidirectional Attention
3.6. Output Layer
4. Experiments
4.1. Experimental Datasets
4.2. Experimental Settings
4.3. Model for Comparison
4.3.1. Syntactic-Based Model
4.3.2. Neural Network Models
4.4. Results and Analysis
4.4.1. Effectiveness of ATGCN
4.4.2. Ablation Experiment
4.4.3. Impact of GCN Layers
4.4.4. Case Study
5. Conclusions and Future
Author Contributions
Funding
Acknowledgments
Conflicts of Interest
References
- Zhang, L.; Liu, B. Sentiment Analysis and Opinion Mining. Synth. Lect. Hum. Lang. Technol. 2016, 30, 167. [Google Scholar]
- Xue, W.; Li, T. Aspect Based Sentiment Analysis with Gated Convolutional Networks. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, Melbourne, Australia, 15–20 July 2018; Volume 1, pp. 2514–2523. [Google Scholar]
- Wang, Y.; Huang, M.; Zhu, X.; Zhao, L. Attention-based LSTM for Aspect-level Sentiment Classification. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, Austin, TX, USA, 1–5 November 2016; pp. 606–615. [Google Scholar]
- Li, X.; Bing, L.; Li, P.; Lam, W. A Unified Model for Opinion Target Extraction and Target Sentiment Prediction. In Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence, Honolulu, HI, USA, 27 January–1 February 2019; pp. 6714–6721. [Google Scholar]
- Ruder, S.; Ghaffari, P.; Breslin, J.G. A Hierarchical Model of Reviews for Aspect-based Sentiment Analysis. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, Austin, TX, USA, 1–5 November 2016; pp. 999–1005. [Google Scholar]
- Minh, V.; Heess, N.; Graves, A. Recurrent models of visual attention. In Proceedings of the Advances in Neural Information Processing Systems 27, Montreal, QC, Canada, 8–13 December 2014; pp. 2204–2212. [Google Scholar]
- Cho, K.; van Merrienboer, B.; Gulcehre, C.; Bahdanau, D.; Bougares, F.; Schwenk, H.; Bengio, Y. Learning phrase representations using RNN encoder-decoder for statistical machine translation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, Doha, Qatar, 25–29 October 2014; pp. 1724–1734. [Google Scholar]
- Gu, S.; Zhang, L.; Song, H.; Hou, Y. A position-aware bidirectional attention network for aspect-level sentiment analysis. In Proceedings of the 27th International Conference on Computational Linguistics, Santa Fe, NM, USA, 20–26 August 2018; pp. 774–784. [Google Scholar]
- Andreas, J.; Rohrbach, M.; Darrell, T. Learning to compose neural networks for question answering. In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, San Diego, CA, USA, 12–17 June 2016; pp. 1545–1554. [Google Scholar]
- Ma, D.; Li, S.; Zhang, X.; Wang, H. Interactive attention networks for aspect-level sentiment classification. In Proceedings of the 26th International Joint Conference on Artificial Intelligence, Melbourne, Australia, 19–25 August 2017; pp. 4068–4074. [Google Scholar]
- Qi, X.; Liao, R.; Jia, J.; Fidler, S.; Urtasun, R. 3D Graph Neural Networks for RGBD Semantic Segmentation. In Proceedings of the 2017 IEEE International Conference on Computer Vision, Venice, Italy, 22–29 October 2017; pp. 5209–5218. [Google Scholar]
- Li, Y.; Ouyang, W.; Zhou, B.; Shi, J.; Zhang, C.; Wang, X. Factorizable Net: An Efficient Subgraph-based Framework for Scene Graph Generation. In Proceedings of the 15th European Conference on Computer Vision, Munich, Germany, 8–14 September 2018; pp. 346–363. [Google Scholar]
- Defferrard, M.; Bresson, X.; Vandergheynst, P. Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering. In Proceedings of the NIPS 2016, Barcelona, Spain, 5–10 December 2016; pp. 3837–3845. [Google Scholar]
- Zhang, M.; Zhang, Y.; Vo, D. Gated neural networks for targeted sentiment analysis. In Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, Phoenix, AZ, USA, 12–17 February 2016; pp. 3087–3093. [Google Scholar]
- He, R.; Lee, W.S.; Ng, H.T.; Dahlmeier, D. Exploiting Document Knowledge for Aspect-level Sentiment Classification. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, Melbourne, Australia, 15–12 July 2018; Volume 2, pp. 579–585. [Google Scholar]
- Zhou, J.; Chen, Q.; Huang, J.X.; Hu, Q.V.; He, L. Position-Aware Hierarchical Transfer Model for Aspect-Level Sentiment Classification. Inform. Sci. 2020, 513, 1–16. [Google Scholar] [CrossRef]
- Tang, D.; Qin, B.; Feng, X.; Liu, T. Effective LSTMs for Target-Dependent Sentiment Classification. In Proceedings of the 26th International Conference on Computational Linguistics, Osaka, Japan, 11–16 December 2016; pp. 3298–3307. [Google Scholar]
- Tang, D.; Qin, B.; Liu, T. Aspect level sentiment classification with deep memory network. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, Austin, TX, USA, 1–5 November 2016; pp. 214–224. [Google Scholar]
- Ma, Y.; Peng, H.; Cambria, E. Targeted Aspect-Based Sentiment Analysis via Embedding Commonsense Knowledge into an Attentive LSTM. In Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, New Orleans, LA, USA, 2–7 February 2018; pp. 5876–5883. [Google Scholar]
- Jianming, Z.; Fei, C.; Taihua, S.; Chen, H. Self-Interaction Attention Mechanism-Based Text Representation for Document Classification. Appl. Sci. 2018, 8, 613. [Google Scholar]
- Wang, J.; Li, J.; Li, S.; Kang, Y.; Zhang, M.; Si, L.; Zhou, G. Aspect sentiment classification with both word-level and clause-level attention networks. In Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, Stockholm, Sweden, 13–19 July 2018; pp. 4439–4445. [Google Scholar]
- Nguyen, H.T.; Nguyen, M.L. Effective Attention Networks for Aspect-level Sentiment Classification. In Proceedings of the 10th International Conference on Knowledge and Systems Engineering, Ho Chi Minh City, Vietnam, 1–3 November 2018; pp. 25–30. [Google Scholar]
- Qiang, Y.; Li, X.; Zhu, D. Toward Tag-free Aspect Based Sentiment Analysis: A Multiple Attention Network Approach. In Proceedings of the 2020 International Joint Conference on Neural Networks, Glasgow, UK, 19–24 July 2020. [Google Scholar]
- Wang, R.; Tao, Z. Interactive Attention Encoder Network with Local Context Features for Aspect-Level Sentiment Analysis. In Proceedings of the 2020 IEEE/CIC International Conference on Communications in China, Chongqing, China, 9–11 August 2020. [Google Scholar]
- Kim, H.; Jeong, Y.S. Sentiment Classification Using Convolutional Neural Networks. Appl. Sci. 2019, 9, 2347. [Google Scholar] [CrossRef] [Green Version]
- Lee, J.; Park, J.; Kim, K.L.; Nam, J. Samplecnn: End-to-End Deep Convolutional Neural Networks Using Very Small Filters for Music Classification. Appl. Sci. 2018, 8, 150. [Google Scholar] [CrossRef] [Green Version]
- Marcheggiani, D.; Titov, I. Encoding sentences with graph convolutional networks for semantic role labeling. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, Copenhagen, Denmark, 7–11 September 2017; pp. 1507–1516. [Google Scholar]
- Bastings, J.; Titov, I.; Aziz, W.; Marcheggiani, D.; Simaan, K. Graph convolutional encoders for syntax-aware neural machine translation. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, Copenhagen, Denmark, 7–11 September 2017; pp. 1947–1957. [Google Scholar]
- Li, Y.; Jin, R.; Luo, Y. Classifying relations in clinical narratives using segment graph convolutional and recurrent neural networks (Seg-GCRNs). J. Am. Med. Inform. Assoc. JAMIA 2018, 26, 262–268. [Google Scholar] [CrossRef] [PubMed]
- Thomas, N.K.; Welling, M. Semi-Supervised Classification with Graph Convolutional Networks. Available online: https://arxiv.org/abs/1609.02907 (accessed on 12 December 2020).
- Zhang, C.; Li, Q.; Song, D. Aspect-based sentiment classification with aspect-specific graph convolutional networks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing, Hong Kong, China, 3–7 November 2019; pp. 4568–4578. [Google Scholar]
- Yao, L.; Mao, C.; Luo, Y. Graph Convolutional Networks for Text Classification. In Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence, Honolulu, HI, USA, 27 January–1 February 2019; pp. 7370–7377. [Google Scholar]
- Peng, H.; Li, J.; He, Y.; Liu, Y.; Bao, M.; Wang, L.; Song, Y.; Yong, Q. Large-Scale Hierarchical Text Classification with Recursively Regularized Deep Graph-CNN. In Proceedings of the 2018 World Wide Web Conference, Lyon, France, 23–27 April 2018; pp. 1063–1072. [Google Scholar]
- Zhang, Y.; Qi, P.; Christopher, D.M. Graph convolutional over pruned dependency trees improves relation extraction. In Proceedings of the EMNLP, Brussels, Belgium, 31 October–4 November 2018; pp. 2205–2215. [Google Scholar]
- Marcheggiani, D.; Bastings, J.; Titov, I. Exploiting Semantics in Neural Machine Translation with Graph Convolutional Networks. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, New Orleans, LA, USA, 1–6 June 2018; Volume 2, pp. 486–492. [Google Scholar]
- Li, X.; Bing, L.; Lam, W.; Shi, B. Transformation Networks for Target-Oriented Sentiment Classification. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, Melbourne, Australia, 15–20 July 2018; Volume 1, pp. 946–956. [Google Scholar]
- Dong, L.; Wei, F.; Tan, C.; Tang, D.; Zhou, M.; Xu, K. Adaptive recursive neural network for target-dependent twitter sentiment classification. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, Baltimore, MD, USA, 23–25 June 2014; Volume 2, pp. 49–54. [Google Scholar]
- Pontiki, M.; Galanis, D.; Pavlopoulos, J.; Papageorgiou, H.; Androutsopoulos, I.; Manandhar, S. SemEval-2014 task 4: Aspect based sentiment analysis. In Proceedings of the International Workshop on Semantic Evaluation, Dublin, Ireland, 23–24 August 2014; pp. 27–35. [Google Scholar]
- Kingma, D.P.; Ba, J. Adam: A method for stochastic optimization. In Proceedings of the 3rd International Conference for Learning Representations, San Diego, CA, USA, 7–9 May 2015. [Google Scholar]
- Nguyen, T.H.; Shirai, K. PhraseRNN: Phrase Recursive Neural Network for Aspect-based Sentiment Analysis. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, Lisbon, Portugal, 17–21 September 2015; pp. 2509–2514. [Google Scholar]
- Sun, C.; Huang, L.; Qiu, X. Utilizing BERT for Aspect-Based Sentiment Analysis via Constructing Auxiliary Sentence. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Minneapolis, MN, USA, 2–7 June 2019; Volume 1, pp. 380–385. [Google Scholar]
- Wang, Q.; Liu, P.; Zhu, Z.; Yin, H.; Zhang, Q.; Zhang, L. A Text Abstraction Summary Model Based on BERT Word Embedding and Reinforcement Learning. Appl. Sci. 2019, 9, 4701. [Google Scholar] [CrossRef] [Green Version]
Dataset | Positive | Neural | Negative | |||
---|---|---|---|---|---|---|
Train | Test | Train | Test | Train | Test | |
1561 | 173 | 3127 | 346 | 1560 | 173 | |
Restaurant | 2164 | 728 | 637 | 196 | 807 | 196 |
Laptop | 994 | 341 | 464 | 169 | 870 | 128 |
Model | Lap14 | Rest14 | ||||
---|---|---|---|---|---|---|
Acc | F1 | Acc | F1 | Acc | F1 | |
AdaRNN | 66.30 | 65.90 | - | - | 60.42 | 45.73 |
PhraseRNN | - | - | - | - | 66.20 | 59.32 |
LSTM+SynATT+TarRep | 70.46 | 67.55 | 70.87 | 66.53 | 79.33 | 69.25 |
TD-LSTM | 70.80 | 69.00 | 68.13 | - | 75.63 | - |
ATAE-LSTM | - | - | 68.70 | - | 77.20 | - |
MemNet | 71.48 | 69.90 | 70.64 | 65.17 | 79.61 | 69.64 |
IAN | 72.50 | 70.81 | 72.05 | 67.38 | 79.26 | 70.09 |
AEN | 72.83 | 69.81 | 73.51 | 69.04 | 80.98 | 72.14 |
BERT-pair-QA-M | 74.28 | 72.38 | 78.21 | 73.56 | 81.96 | 73.29 |
ASGCN | 72.15 | 70.40 | 75.55 | 71.05 | 80.77 | 72.02 |
ATGCN(Glove) | 73.02 | 70.98 | 75.92 | 71.70 | 81.85 | 73.31 |
ATGCN(BERT) | 74.26 | 73.81 | 80.06 | 75.61 | 82.79 | 75.10 |
ASGCN | ATGCN (GloVe) | |
---|---|---|
GPU | 2080ti | 20180ti |
Programing language | Python 3.6 | Python 3.6 |
Pytorch | 1.1.0 | 1.1.0 |
Training Time | 5.5 h | 4 h |
Model | Lap14 | Rest14 | ||||
---|---|---|---|---|---|---|
Acc | F1 | Acc | F1 | Acc | F1 | |
ATGCN w/o pos | 73.16 | 70.63 | 72.39 | 68.15 | 81.03 | 73.52 |
ATGCN w/o Biatt | 72.80 | 69.59 | 72.07 | 69.25 | 78.83 | 69.01 |
ATGCN-Siatt | 72.91 | 69.73 | 73.68 | 69.93 | 79.37 | 70.95 |
ATCNN | 72.65 | 70.83 | 73.64 | 68.91 | 79.24 | 69.57 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
Share and Cite
Liu, J.; Liu, P.; Zhu, Z.; Li, X.; Xu, G. Graph Convolutional Networks with Bidirectional Attention for Aspect-Based Sentiment Classification. Appl. Sci. 2021, 11, 1528. https://doi.org/10.3390/app11041528
Liu J, Liu P, Zhu Z, Li X, Xu G. Graph Convolutional Networks with Bidirectional Attention for Aspect-Based Sentiment Classification. Applied Sciences. 2021; 11(4):1528. https://doi.org/10.3390/app11041528
Chicago/Turabian StyleLiu, Jie, Peiyu Liu, Zhenfang Zhu, Xiaowen Li, and Guangtao Xu. 2021. "Graph Convolutional Networks with Bidirectional Attention for Aspect-Based Sentiment Classification" Applied Sciences 11, no. 4: 1528. https://doi.org/10.3390/app11041528
APA StyleLiu, J., Liu, P., Zhu, Z., Li, X., & Xu, G. (2021). Graph Convolutional Networks with Bidirectional Attention for Aspect-Based Sentiment Classification. Applied Sciences, 11(4), 1528. https://doi.org/10.3390/app11041528