Abstract
Recently, recurrent neural networks (RNN) have achieved great success in the aspect-based sentiment classification task. Existing approaches always focus on capture the local (attentive) representation or global representation independently, while how to integrate them is not well studied. To address this problem, we propose a Position-Gated Recurrent Neural Networks (PG-RNN) model that considered aspect word position information. PG-RNN can integrate global and local information dynamically for aspect-based sentiment classification. Specifically, first, we propose a positional RNN model to integrate the aspect position information into the sentence encoder to enhance the latent representation. Unlike the existing work, we use kernel function to model position information instead of discrete distance values. Second, we design a representation absorption gating to absorb local positional representation and global representation dynamically. Experiments on five benchmark datasets show the significant advantages of our proposed model. More specifically, we achieve a maximum improvement of 7.38% over the classic attention-based RNN model in terms of accuracy.
Similar content being viewed by others
Notes
Particularly, more kernel functions can be used to measure the distances though we only evaluate on two classic ones.
References
Liu Bing (2012) Sentiment analysis and opinion mining. Synth Lect Hum Lang Technol 5(1):1–167
Zhou Jie , Tian Junfeng , Wang Rui, Wu Yuanbin, Xiao Wenming, He Liang (2020). Sentix: A sentiment-aware pre-trained model for cross-domain sentiment analysis. In: Proceedings of the 28th International Conference on Computational Linguistics, pp. 568–579
Jie Zhou, Yuanbin Wu, Changzhi Sun, and Liang He. (2021) Is “hot pizza” positive or negative? mining target-aware sentiment lexicons. In: Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pp. 608–618
Cambria Erik, Poria Soujanya, Bajpai Rajiv, Schuller Björn (2016) Senticnet 4: a semantic resource for sentiment analysis based on conceptual primitives. COLING, Technical Papers, In, pp 2666–2677
J Cheng, S Zhao, J Zhang, I King, X Zhang, and H Wang. (2017) Aspect-level sentiment classification with heat (hierarchical attention) network. In: CIKM, pp. 97–106
M Pontiki, D Galanis, H Papageorgiou, I Androutsopoulos, S Manandhar, M AL-Smadi, M Al-Ayyoub, Y Zhao, B Qin, O De Clercq, et al. (2016) Semeval-2016 task 5: aspect based sentiment analysis. In: SemEval-2016, pp. 19–30
Schouten K, Frasincar F (2016) Survey on aspect-level sentiment analysis. TKDE 1(1):1
Jie Z, Qin C, Xiangji HJ, Vivian HQ, Liang H (2020) Position-aware hierarchical transfer model for aspect-level sentiment classification. Inf Sci 513:1–16
Zhou J, Jimmy XH, Qinmin VH, He L (2020) Sk-gcn: modeling syntax and knowledge via graph convolutional network for aspect-level sentiment classification. Knowl-Based Syst 205:106292
Tang D, Q Bing, F Xiaocheng, L Ting (2016). Effective LSTMs for target-dependent sentiment classification. In: COLING, pp. 3298–3307
C dos Santos, M Tan, B Xiang, and B Zhou. (2016) Attentive pooling networks. arXiv preprint arXiv:1602.03609
Xu L, Liu J, Wang L, Yin C (2017). Aspect based sentiment analysis for online reviews. In: Advances in Computer Science and Ubiquitous Computing, pp. 475–480
H Zhao, Z Lu, and P Poupart. (2015) Self-adaptive hierarchical sentence model. In: IJCAI, pp. 4069–4076
Zhou C, Sun C, Liu Z, Lau F (2015). A C-LSTM neural network for text classification. arXiv preprint arXiv:1511.08630
J Liu, Y Zhang (2017) Attention modeling for targeted sentiment. In: ACL: Volume 2, Short Papers, pp. 572–577
Ma D, Li S, Zhang X, Wang H (2017). Interactive attention networks for aspect-level sentiment classification. In: IJCAI, pp. 4068–4074
Y Wang, M Huang, L Zhao, et al. (2016) Attention-based LSTM for aspect-level sentiment classification. In: ACL, pp. 606–615
Yang M, Tu W, Wang J, Xu F, Chen X (2017). Attention based LSTM for target dependent sentiment classification. In: AAAI, pp. 5013–5014
P Chen, Z Sun, L Bing, and W Yang. (2017) Recurrent attention network on memory for aspect sentiment analysis. In: EMNLP, pp. 452–461
Li X, Bing L, Lam W, Shi B (2018) Transformation networks for target-oriented sentiment classification. In: ACL
X Li and W Lam. (2017) Deep multi-task learning for aspect term extraction with memory interaction. In: EMNLP, pp. 2886–2892
Tang D, Qin B, Liu T (2016) . Aspect level sentiment classification with deep memory network. In: ACL, pp. 214–224
A Vaswani, N Shazeer, N Parmar, J Uszkoreit, L Jones, AN Gomez, L Kaiser, and I Polosukhin. (2017) Attention is all you need. In: Advances in neural information processing systems, pp. 5998–6008
L Dong, F Wei, C Tan, D Tang, M Zhou, and K Xu (2014) Adaptive recursive neural network for target-dependent twitter sentiment classification. In: ACL: Volume 2, Short Papers, vol 2, pp. 49–54
Jiang L, Mo Y, Zhou M, Liu X, Zhao T (2011) Target-dependent twitter sentiment classification. ACL: HLT 1:151–160
Kiritchenko S, Zhu X, Cherry C, Mohammad S (2014) Detecting aspects and sentiment in customer reviews. SemEval 2014:437–442
Nguyen TH, Shirai K (2015). Phrasernn: phrase recursive neural network for aspect-based sentiment analysis. In: EMNLP, pp. 2509–2514
Vo DT, Zhang Y (2015). Target-dependent twitter sentiment classification with rich automatic features. In: IJCAI, pp. 1347–1353
Jianxing Y, Zha ZJ, Wang M, Chua TS (2011) Aspect ranking: identifying important product aspects from online consumer reviews. ACL: HLT-Volume 1:1496–1505
Zhang M, Zhang Y, Vo DT (2016). Gated neural networks for targeted sentiment analysis. In: AAAI, pp. 3087–3093
Pang Bo, Lee Lillian, Vaithyanathan Shivakumar (2002) Thumbs up?: sentiment classification using machine learning techniques. ACL 10:79–86
He R, WS Lee, HT Ng, and D Dahlmeier (2018) Exploiting document knowledge for aspect-level sentiment classification, In: ACL
J Tang, Z Lu, J Su, Y Ge, L Song, L Sun, and J Luo. (2019) Progressive self-supervised attention learning for aspect-level sentiment analysis. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 557–566
Hochreiter Sepp, Schmidhuber Jürgen (1997) Long short-term memory. Neural Comput 9(8):1735–1780
Bahdanau D, Cho K, Bengio Y (2014). Neural machine translation by jointly learning to align and translate. In: CoRR, abs/1409.0473
Y Ma, H Peng, and E Cambria. (2018) Targeted aspect-based sentiment analysis via embedding commonsense knowledge into an attentive lstm. In: AAAI
Zhang C, Li Q, Song D (2019). Aspect-based sentiment classification with aspect-specific graph convolutional 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), pp. 4560–4570
K Sun, R Zhang, S Mensah, Y Mao, and X Liu (2019) Aspect-level sentiment analysis via convolution over dependency tree. 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), pp. 5683–5692
Wang S, Lo D, Xing Z, Jiang L (2011). Concern localization using information retrieval: an empirical study on linux kernel. In: 2011 18th Working Conference on Reverse Engineering, IEEE. pp. 92–96
Moschitti Alessandro, Quarteroni Silvia (2011) Linguistic kernels for answer re-ranking in question answering systems. Inf Process Manag 47(6):825–842
D Wang and E Nyberg. (2015) A long short-term memory model for answer sentence selection in question answering. In: ACL: Volume 2, Short Papers, vol 2, pp. 707–712
Luong MT, Pham H, Manning CD (2015). Effective approaches to attention-based neural machine translation. In: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pp. 1412–1421
Zhao J, Huang JX, Ye Z (2014) Modeling term associations for probabilistic information retrieval. TOIS 32(2):7
Jozefowicz R, Zaremba W, Sutskever I (2015). An empirical exploration of recurrent network architectures. In: ICML, pp. 2342–2350
L Dong, F Wei, C Tan, D Tang, M Zhou, and K Xu. (2014) Adaptive recursive neural network for target-dependent twitter sentiment classification. In: Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014, June 22-27, 2014, Baltimore, MD, USA, Volume 2: Short Papers, pp. 49–54
Chung J , Gulcehre C, Cho K, Bengio Y (2014). Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555
J Pennington, R Socher, and C Manning (2014) Glove: global vectors for word representation. In: EMNLP, pp. 1532–1543
Tieleman T, Hinton G (2012) Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude. COURSERA: Neural Netw Mach Learn 4(2):26–31
J Pennington, R Socher, and CD Manning (2014) Glove: global vectors for word representation. In Alessandro Moschitti, Bo Pang, and Walter Daelemans, editors, Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014, October 25-29, 2014, Doha, Qatar, A meeting of SIGDAT, a Special Interest Group of the ACL, pp. 1532–1543
Li Z, Ying Wei Y, Xiang ZZ, Li X (2019) Exploiting coarse-to-fine task transfer for aspect-level sentiment classification. Proceed AAAI Conf Artif Intell 33:4253–4260
Acknowledgements
We greatly appreciate anonymous reviewers and the associate editor for their valuable and high quality comments that greatly helped to improve the quality of this article. This research is funded by the Science and Technology Commission of Shanghai Municipality (19511120200).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Bai, Q., Zhou, J. & He, L. PG-RNN: using position-gated recurrent neural networks for aspect-based sentiment classification. J Supercomput 78, 4073–4094 (2022). https://doi.org/10.1007/s11227-021-04019-5
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11227-021-04019-5