Abstract
Aspect-level sentiment classification aims to identify the polarity of a target word in a sentence. Studies on sentiment classification have found that a target’s surrounding words have great impacts and global attention to the target. However, existing neural-network-based models either depend on expensive phrase-level annotation or do not fully exploit the association of the context words to the target. In this paper, we propose to model the influences of the target’s surrounding words via two unidirectional long short-term memory neural networks, and introduce a target-based attention mechanism to discover the underlying relationship between the target and the context words. Empirical results on the SemEval 2014 Datasets show that our approach outperforms many competitive sentiment classification baseline methods. Detailed analysis demonstrates the effectiveness of the proposed surrounding-based long-short memory neural networks and the target-based attention mechanism.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
Detailed information can be found at: http://alt.qcri.org/semeval2014/task4.
- 2.
Available at: https://nlp.stanford.edu/projects/glove/.
References
Dinsoreanu, M., Bacu, A.: Unsupervised Twitter sentiment classification. In: KMIS, pp. 220–227 (2014). https://doi.org/10.5220/0005079002200227
Dong, L., Wei, F., Zhou, M., Xu, K.: Adaptive multi-compositionality for recursive neural models with applications to sentiment analysis. In: AAAI, pp. 1537–1543 (2014). https://doi.org/10.1109/TASLP.2015.2509257
Ganchev, T.D., Parsopoulos, K.E., Vrahatis, M.N., Fakotakis, N.D.: Partially connected locally recurrent probabilistic neural networks (2008). https://doi.org/10.5772/5552
Hearst, M.A., Dumais, S.T., Osuna, E., Platt, J., Scholkopf, B.: Support vector machines. IEEE Intell. Syst. Their Appl. 13(4), 18–28 (1998). https://doi.org/10.1016/j.neunet.2010.01.002
Heeger, D.J., Gandhi, S.P., Huk, A.C., Boynton, G.M.: Neuronal correlates of attention in human visual cortex, pp. 25–47. The MIT Press, Cambridge (2001). https://doi.org/10.7551/mitpress/7125.003.0004
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997). https://doi.org/10.4324/9781315174105-4
Kim, Y.: Convolutional neural networks for sentence classification. arXiv preprint arXiv:1408.5882 (2014). https://doi.org/10.3115/v1/d14-1181
Kurata, G., Ramabhadran, B., Saon, G., Sethy, A.: Language modeling with highway LSTM. In: ASRU, pp. 244–251. IEEE (2017). https://doi.org/10.1109/asru.2017.8268942
Liu, J., Zhang, Y.: Attention modeling for targeted sentiment. In: EACL, vol. 2, pp. 572–577 (2017). https://doi.org/10.18653/v1/e17-2091
Ma, D., Li, S., Zhang, X., Wang, H.: Interactive attention networks for aspect-level sentiment classification. arXiv preprint arXiv:1709.00893 (2017). https://doi.org/10.24963/ijcai.2017/568
Ma, Y., Peng, H., Cambria, E.: Targeted aspect-based sentiment analysis via embedding commonsense knowledge into an attentive LSTM. In: AAAI (2018). https://doi.org/10.1007/s12559-018-9549-x
Mubarok, M.S., Adiwijaya, Aldhi, M.D.: Aspect-based sentiment analysis to review products using Naïve Bayes. In: AIPC, vol. 1867, p. 020060. AIP Publishing (2017). https://doi.org/10.1063/1.4994463
Pang, B., Lee, L., et al.: Opinion mining and sentiment analysis. FTIR 2(1–2), 1–135 (2008). https://doi.org/10.4000/books.oep.223
Pennington, J., Socher, R., Manning, C.: GloVe: global vectors for word representation. In: EMNLP, pp. 1532–1543 (2014). https://doi.org/10.3115/v1/d14-1162
Qian, Q., Huang, M., Lei, J., Zhu, X.: Linguistically regularized LSTMs for sentiment classification. arXiv preprint arXiv:1611.03949 (2016). https://doi.org/10.18653/v1/p17-1154
Shen, H.: Towards a mathematical understanding of the difficulty in learning with feedforward neural networks. In: CVPR, pp. 811–820 (2018). https://doi.org/10.1109/cvpr.2018.00091
Singla, Z., Randhawa, S., Jain, S.: Sentiment analysis of customer product reviews using machine learning. In: 2017 International Conference on Intelligent Computing and Control (I2C2), pp. 1–5. IEEE (2017). https://doi.org/10.1109/i2c2.2017.8321910
Tai, K.S., Socher, R., Manning, C.D.: Improved semantic representations from tree-structured long short-term memory networks. arXiv preprint arXiv:1503.00075 (2015). https://doi.org/10.3115/v1/p15-1150
Tang, D., Qin, B., Liu, T.: Aspect level sentiment classification with deep memory network. arXiv preprint arXiv:1605.08900 (2016). https://doi.org/10.18653/v1/d16-1021
Übeyli, E.D., Übeyli, M.: Case studies for applications of Elman recurrent neural networks (2008). https://doi.org/10.5772/5550
Wald, R., Khoshgoftaar, T.M., Napolitano, A.: Stability of filter-and wrapper-based feature subset selection. In: ICTAI, pp. 374–380. IEEE (2013). https://doi.org/10.1109/ictai.2013.63
Wang, H., Zhang, X., Liang, B., Zhou, Q., Xu, B.: Gated hierarchical LSTMs for target-based sentiment analysis. Int. J. Softw. Eng. Knowl. Eng. 28(11n12), 1719–1737 (2018). https://doi.org/10.18293/seke2018-093
Wang, Y., Huang, M., Zhao, L., et al.: Attention-based LSTM for aspect-level sentiment classification. In: EMNLP, pp. 606–615 (2016). https://doi.org/10.18653/v1/d16-1058
Yang, T.H., Tseng, T.H., Chen, C.P.: Recurrent neural network-based language models with variation in net topology, language, and granularity. In: IALP, pp. 71–74. IEEE (2016). https://doi.org/10.1109/ialp.2016.7875937
Acknowledgments
This work is supported by the Humanities and Social Sciences Fund of Ministry of Education (13YJC870023) and the National Social Science Fund of China (15BTQ056).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Sun, Y., Wang, X., Liu, H., Wang, W., Jiao, P. (2019). Surrounding-Based Attention Networks for Aspect-Level Sentiment Classification. In: Tetko, I., Kůrková, V., Karpov, P., Theis, F. (eds) Artificial Neural Networks and Machine Learning – ICANN 2019: Text and Time Series. ICANN 2019. Lecture Notes in Computer Science(), vol 11730. Springer, Cham. https://doi.org/10.1007/978-3-030-30490-4_13
Download citation
DOI: https://doi.org/10.1007/978-3-030-30490-4_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-30489-8
Online ISBN: 978-3-030-30490-4
eBook Packages: Computer ScienceComputer Science (R0)