Target Information Fusion Based on Memory Network for Aspect-Level Sentiment Classification

  • Zhaochuan Wei
  • Jun Peng
  • Xiaodong CaiEmail author
  • Guangming He
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 895)


Aspect-level sentiment classification is a fine-grained task that provides more complete and deeper analysis results. Attention networks are widely used for aspect-level sentiment classification task. However, when multiple target words in a sentence contain opposite sentiments or the expressions of different targets are similar, the network tends to perform poorly. Our studies find that the method of averaging a sentence or target words weakens the capacity of key words. A target information fusion memory network is proposed to solve this problem in this paper. Firstly, the feature of sentences is extracted through a Bi-LSTM network. Then, the feature of target is extracted incorporated into the sentence feature extracted. Then, the memory information of the specific target is formed by the position coding. Finally, the recurrent attention network is utilized to extract the sentiment expression from the memory. Compare with IAN, the method proposed achieves 1.5% and 1.9% accuracy improvement on SemEvil2014 restaurant dataset and self-defined Chinese mobile phone dataset, respectively. A further extend experiment proves that the proposed method can effectively improve the performance in the case of complex sentences.


Aspect-level sentiment classification Interactive attention neural network Memory network Information fusion 



Our work is supported by Key Research and Development Projects of Xinjiang Autonomous Region in 2018 (No. 2018B03022-1 and No. 2018B03022-2), Innovation Project of GUET Graduate Education (No. 2018YJCX38 and No. 2017YJCX38) and Key Research and Guangxi Director Fund of the Key Laboratory of Wireless Broadband Communication and Signal Processing (No. GXKL0614107).


  1. 1.
    Zhang, L., Liu, B.: Sentiment analysis and opinion mining. Synth. Lect. Hum. Lang. Technol. 30(1), 1–167 (2016)Google Scholar
  2. 2.
    Zhang, L., Wang, S., Liu, B.: Deep learning for sentiment analysis: a survey. Wiley Interdiscip. Rev. Data Min. Knowl. Discov. (2018)Google Scholar
  3. 3.
    Ding, X., Liu, B., Yu, P.S.: A holistic lexicon-based approach to opinion mining. In: Proceedings of the 2008 International Conference on Web Search and Data Mining, pp. 231–240 (2008)Google Scholar
  4. 4.
    Perez-Rosas, V., Banea, C., Mihalcea, R.: Learning sentiment lexicons in Spanish. European Language Resources Association (ELRA) (2012)Google Scholar
  5. 5.
    Tang, D., Qin, B., Feng, X., Liu, T.: Effective LSTMs for target-dependent sentiment classification. Comput. Sci. (2015)Google Scholar
  6. 6.
    Wang, Y., Huang, M., Zhu, X., Zhao, L.: Attention-based LSTM for aspect-level sentiment classification. In: Conference on Empirical Methods in Natural Language Processing, pp. 606–615 (2017)Google Scholar
  7. 7.
    Tang, D., Qin, B., Liu, T.: Aspect level sentiment classification with deep memory network. In: Conference on Empirical Methods in Natural Language Processing, pp. 214–224 (2016)Google Scholar
  8. 8.
    Ma, D., Li, S., Zhang, X., Wang, H.: Interactive attention networks for aspect-level sentiment classification. In: Twenty-Sixth International Joint Conference on Artificial Intelligence, pp. 4068–4074 (2017)Google Scholar
  9. 9.
    Chen, P., Sun, Z., Bing, L., Yang, W.: Recurrent attention network on memory for aspect sentiment analysis. In: Conference on Empirical Methods in Natural Language Processing, pp. 452–461 (2017)Google Scholar
  10. 10.
    Li, X., Bing, L., Lam, W., Shi, B.: Transformation networks for target-oriented sentiment classification, pp. 946–956. Association for Computational Linguistics (2018)Google Scholar
  11. 11.
    He, R., Lee, W.S., Ng, H.T., Dahlmeier, D.: Exploiting document knowledge for aspect-level sentiment classification, pp. 579–585. Association for Computational Linguistics (2018)Google Scholar
  12. 12.
    Hazarika, D., Poria, S., Vij, P., Krishnamurthy, G., Cambria, E., Zimmermann, R.: Modeling inter-aspect dependencies for aspect-based sentiment analysis. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pp. 266–270 (2018)Google Scholar
  13. 13.
    Pennington, J., Socher, R., Manning, C.: Glove: Global vectors for word representation. In: Conference on Empirical Methods in Natural Language Processing, pp. 1532–1543 (2014)Google Scholar
  14. 14.
    Mikolov, T., Sutskever, I., Chen, K., Corrado, G., Dean, J.: Distributed representations of words and phrases and their compositionality. In: International Conference on Neural Information Processing Systems, pp. 3111–3119. Curran Associates Inc. (2013)Google Scholar
  15. 15.
    Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)MathSciNetzbMATHGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Zhaochuan Wei
    • 1
  • Jun Peng
    • 1
  • Xiaodong Cai
    • 1
    Email author
  • Guangming He
    • 2
  1. 1.Guilin University of Electronic TechnologyGuilinChina
  2. 2.China Comservice Public Information Industry Co., Ltd.UrumqiChina

Personalised recommendations