Abstract
Aspect-level sentiment analysis can provide more detailed information than general sentiment analysis, because it aims to predict the sentiment polarities of the given aspects or entities in text. The state-of-the-art neural models use RNN with attention seems a good method for the characteristics of this task in English, but because of the complexity of Chinese texts and the difference between Chinese and English, English learning outcomes cannot be directly applied to Chinese. After re-examining the drawbacks of attention mechanism and obstacles that Chinese aspect-level sentiment analysis, we build upon line of research and propose three approaches overcome these issues. First, we propose a mixed vector to enhance the information embedded in Chinese word embedding. Second, we introduce an attention weight calculate method for target representation that better captures the semantic meaning of the opinion target. Third, we use CNN to extract local information in the text. The experimental results show that our model consistently outperforms the state-of-the-art methods on Chinese reviews.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Chen, P., Sun, Z.Z., Bing, L.D., Yang, W.: Recurrent attention network on memory for aspect sentiment analysis. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp. 463–472 (2017)
Socher, R., Pennington, J., Huang, E.H., Ng, A.Y., Manning, C.D.: Semi-supervised recursive autoencoders for predicting sentiment distributions. In: Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing, EMNLP 2011, pp. 151–161 (2011)
Appel, O., Chiclana, F., Carter, J., Fujita, H.: A hybrid approach to the sentiment analysis problem at the sentence level. Knowl.-Based Syst. 108, 110–124 (2016)
Chen, H.L., Li, S., Wu, P.H., Yi, N.A., Li, S.Y., Huang, X.R.: Finegrained sentiment analysis of Chinese reviews using LSTM network. J. Eng. Sci. Technol. Rev. 11(1), 174–179 (2018)
Natural Language Computing Group, Microsoft Research Asia: R-NET: Machine Reading Comprehension With Self-matching Networks (2017)
Wang, Y.Q., Huang, M.L., Zhu, X.Y., Zhao, L.: Attention-based LSTM for aspect-level sentiment classification. In: Proceedings of EMNLP, pp. 606–615 (2016)
Tang, D.Y., Qin, B., Liu, T.: Aspect level sentiment classification with deep memory network. In: Proceedings of EMNLP, pp. 214–224 (2016)
Yang, M., Tu, W.T., Wang, J.X., Xu, F., Chen, X.J.: Attention based lstm for target dependent sentiment classification. In: Proceedings of AAAI, pp. 5013–5014 (2017)
Liu, J.M., Zhang, Y.: Attention modeling for targeted sentiment. In: Conference of the European Chapter of the Association for Computational Linguistics (2017)
Ma, D.H., Li, S.J., Zhang, X.D, Wang, H.F.: Interactive attention networks for aspect-level sentiment classification. In:Proceedings of IJCAI, pp. 4068–4074(2017)
Chen, P., Sun, Z.Q., Bing, L.D., Yang,W.: Recurrent attention network on memory for aspect sentiment analysis. In:Proceedings of EMNLP, pp. 463–472(2017)
Tang, D.Y., Qin, B., Feng, X.C., Liu, T.: Effective lstms for target dependent sentiment classification. In: Proceedings of COLING, pp. 3298–3307(2016)
He, R.D., Lee, W.S., Tou Ng, H., Dahlmeier, D.: An unsupervised neural attention model for aspect extraction. In: Annual Meeting of the Association for Computational Linguistics (ACL 2017) (2017)
Lai, S.W., Xu, L.H., Liu, K., Zhao, J.: Recurrent convolutional neural networks for text classification. Proc. AAAI 333, 2267–2273 (2015)
Wang, Y.Q., Huang, M.L., Zhao, L., Zhu, X.Y.: Attention-based LSTM for aspect-level sentiment classification. In: Conference on Empirical Methods in Natural Language Processing (EMNLP 2016) (2016)
Zhang, M.S., Zhang, Y., Duy-Tin, V.: Gated neural networks for targeted sentiment analysis. In: AAAI Conference on Artificial Intelligence (AAAI 2016) (2016)
He, R., Lee, W.S, Ng, H.T.: Effective attention modeling for aspect-level sentiment classification. In: Proceedings of the 27th International Conference on Computational Linguistics, pp. 1121–1131 (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Cheng, K., Wang, Z., Liu, J. (2021). Chinese Aspect-Level Sentiment Analysis CNN-LSTM Based on Mixed Vector. In: Liu, Q., Liu, X., Li, L., Zhou, H., Zhao, HH. (eds) Proceedings of the 9th International Conference on Computer Engineering and Networks . Advances in Intelligent Systems and Computing, vol 1143. Springer, Singapore. https://doi.org/10.1007/978-981-15-3753-0_29
Download citation
DOI: https://doi.org/10.1007/978-981-15-3753-0_29
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-3752-3
Online ISBN: 978-981-15-3753-0
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)