Abstract
Aspect-level sentiment analysis aims to predict the sentiment polarity of a given target in a review sentence. Most of the previous methods focus on capturing the context information of words across the sentence related to the target, ignoring the importance of the independent relationship between the opinion words and the target. To address this limitation, we propose a position-aware hybrid attention network model for aspect-level sentiment analysis, which incorporates not only the context information of words related to the target, but also the independent relationship between the opinion words related to the target. We conduct several comparable experiments on public laptop and restaurant datasets. The experimental results show that our proposed model achieves a more effective performance than the baseline models.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Zeng, J., Ma, X., Zhou, K.: Enhancing attention-based LSTM with position context for aspect-level sentiment classification. IEEE Access 7, 20462–20471 (2019)
Tang, D., Qin, B., Feng, X., Liu, T.: Effective LSTMs for target-dependent sentiment classification. In: COLING 2016, pp. 3298–3307 (2016)
Wang, Y., Huang, M., Zhao, L., Zhu, X.: Attention-based LSTM for aspect-level sentiment classification. In: EMNLP 2016, pp. 606–615 (2016)
Kiritchenko, S., Zhu, X., Cherry, C., Mohammad, S.M.: Detecting aspects and sentiment in customer reviews. In: SemEval@COLING 2014, pp. 437–442 (2014)
Wagner, J., Arora, P., Cortes, S., Barman, U., Bogdanova, D., Foster, J., Tounsi, L.: Aspect-based polarity classification for SemEval task 4. In: SemEval@COLING 2014, pp. 223–229 (2014)
Vo, D.-T., Zhang, Y.: Target-dependent twitter sentiment classification with rich automatic features. In: IJCAI 2015, pp. 1347–1353 (2015)
Tang, D., Qin, B., Liu, T.: Aspect level sentiment classification with deep memory network. In: EMNLP 2016, pp. 214–224 (2016)
Ma, D., Li, S., Zhang, X., Wang, H.: Interactive attention networks for aspect-level sentiment classification. In: IJCAI 2017, pp. 4068–4074 (2017)
Chen, P., Sun, Z., Bing, L., Yang, W.: Recurrent attention network on memory for aspect sentiment analysis. In: EMNLP 2017, pp. 452–461 (2017)
Vaswani, A., et al.: Attention is all you need. In: NIPS 2017, pp. 5998–6008 (2017)
Zheng, S., Xia, R.: Left-center-right separated neural network for aspect-based sentiment analysis with rotatory attention. CoRR abs/1802.00892 (2018)
Tay, Y., Tuan, L.A., Hui, S.C.: Learning to attend via word-aspect associative fusion for aspect-based sentiment analysis. In: AAAI 2018, pp. 5956–5963 (2018)
Huang, B., Ou, Y., Carley, K.M.: Aspect level sentiment classification with attention-over-attention neural networks. In: SBP-BRiMS 2018, pp. 197–206 (2018)
Xue W, Li T.: Aspect Based Sentiment Analysis with Gated Convolutional Networks.. In: ACL 2018. Association for Computational Linguistics, vol. 1, pp. 2514–2523 (2018)
Liu, F., Cohn, T., Baldwin, T.: Recurrent entity networks with delayed memory update for targeted aspect-based sentiment analysis. In: NAACL-HLT 2018, vol. 2, pp. 278–283 (2018)
Majumder, N., Poria, S., Gelbukh, A., Akhtar, S., Cambria, E., Ekbal, A.: IARM: inter-aspect relation modeling with memory networks in aspect-based sentiment analysis. In: EMNLP 2018, pp. 3402–3411 (2018)
Wu, S., Xu, Y., Wu, F., Yuan, Z., Huang, Y., Li, X.: Aspect-based sentiment analysis via fusing multiple sources of textual knowledge. Knowl. Based Syst. 183, 104868 (2019)
Liang, B., Du, J., Xu, R., Li, B., Huang, H.: Context-aware embedding for targeted aspect-based sentiment analysis. In: ACL 2019, vol. 1, pp. 4678–4683 (2019)
Bao, L., Lambert, P., Badia, T.: Attention and lexicon regularized LSTM for aspect-based sentiment analysis. In: ACL 2019, vol. 2, pp. 253–259 (2019)
He, R., Lee, W.S., Ng, H.T., Dahlmeier, D.: An interactive multi-task learning network for end-to-end aspect-based sentiment analysis. In: ACL 2019, vol.1, pp. 504–515 (2019)
Wang, X., Xu, G., Zhang, J., Sun, X., Wang, L., Huang, T.: Syntax-directed hybrid attention network for aspect-level sentiment analysis. IEEE Access 7, 5014–5025 (2019)
Li, L., Liu, Y., Zhou, A.: Hierarchical attention based position-aware network for aspect-level sentiment analysis. In: CoNLL 2018, pp. 181–189 (2018)
Hu, M., Liu, B.: Mining and summarizing customer reviews. In: KDD 2004, pp. 168–177 (2004)
Pennington, J., Socher, R., Manning, C.D.: GloVe: global vectors for word representation. In: EMNLP 2014, pp. 1532–1543 (2014)
Mikolov, T., Chen, K., Corrado, G., Dean, J.: Distributed representations of words and phrases and their compositionality. In: NIPS 2013, pp. 3111–3119 (2013)
Hochreiter, S., Urgen Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Acknowledgements
This work is supported by National Nature Science Foundation of China (61976062), the Science and Technology Program of Guangzhou, China (No. 201904010303 and No. 202002030227) and the Special Funds for the Cultivation of Guangdong College Students’ Scientific and Technological Innovation (“Climbing Program” Special Funds, grant number: pdjh2019b0173).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Zheng, Y., Li, X., Su, G., Ma, J., Ning, C. (2020). Position-aware Hybrid Attention Network for Aspect-Level Sentiment Analysis. In: Dou, Z., Miao, Q., Lu, W., Mao, J., Jia, G. (eds) Information Retrieval. CCIR 2020. Lecture Notes in Computer Science(), vol 12285. Springer, Cham. https://doi.org/10.1007/978-3-030-56725-5_7
Download citation
DOI: https://doi.org/10.1007/978-3-030-56725-5_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-56724-8
Online ISBN: 978-3-030-56725-5
eBook Packages: Computer ScienceComputer Science (R0)