Advertisement

An Integrated Semantic-Syntactic SBLSTM Model for Aspect Specific Opinion Extraction

  • Zhongming HanEmail author
  • Xin Jiang
  • Mengqi Li
  • Mengmei Zhang
  • Dagao Duan
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11242)

Abstract

Opinion Mining (OM) of Internet reviews is one of the key issues in Natural Language Processing (NLP) field. This paper proposes a stacked Bi-LSTM aspect opinion extraction model in which semantic and syntactic features are both integrated. The model takes embedded vector which is composed by word embedding, POS tags and dependency relations as its input while taking label sequence as its output. The experimental results show the effectiveness of this structural features embedded stacked Bi-LSTM model on cross-domain and cross-language datasets, and indicate that this model outperforms the state-of-the-art methods.

Keywords

Aspect Opinion extraction Dependency tree Stacked Bi-LSTM 

References

  1. 1.
    Poria, S., Cambria, E., Gelbukh, A.: Aspect extraction for opinion mining with a deep convolutional neural network. Knowl.-Based Syst. 108, 42–49 (2016)CrossRefGoogle Scholar
  2. 2.
    Hu, M., Liu, B.: Mining and summarizing customer reviews. In: Proceedings of the 10th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2004), pp. 168–177. ACM, New York (2004)Google Scholar
  3. 3.
    Valakunde, N.D., Patwardhan, M.S.: Multi-aspect and multi-class based document sentiment analysis of educational data catering accreditation process. In: International Conference on Cloud & Ubiquitous Computing & Emerging Technologies (CUBE 2013), pp. 188–192. IEEE Computer Society, Washington (2013)Google Scholar
  4. 4.
    Singh, V.K., Piryani, R., Uddin, A., et al.: Sentiment analysis of movie reviews: a new feature-based heuristic for aspect-level sentiment classification. In: International Multi-Conference on Automation, Computing, Communication, Control and Compressed Sensing (iMac4 s 2013), pp. 712–717. IEEE Computer Society, Washington (2013)Google Scholar
  5. 5.
    Pang, L., Lan, Y.Y., Xu, J., et al.: A survey on deep text matching. Chin. J. Comput. 40(04), 985–1003 (2017). (in Chinese with English abstract)MathSciNetGoogle Scholar
  6. 6.
    Socher, R., Perelygin, A., Wu, J.Y., et al.: Recursive deep models for semantic compositionality over a sentiment treebank. In: Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing (EMNLP 2013), pp. 1631–1642. ACL, Stroudsburg, PA (2013)Google Scholar
  7. 7.
    Goller, C., Kuchler, A.: Learning task-dependent distributed representations by backpropagation through structure. In: IEEE International Conference on Neural Networks, vol. 1, pp. 347–352. IEEE (2002)Google Scholar
  8. 8.
    Hochreiter, S., Jurgen, J.: Long short-term memory. Neural Comput. 9, 1735–1780 (1997)CrossRefGoogle Scholar
  9. 9.
    Cho, K., Merrienboer, B.V., Bahdana, D., Bengio, Y.: On the properties of neural machine translation: encoder-decoder approaches. In: Proceedings of SSST-8, Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation, Doha, Qatar, 25 October 2014, pp. 103–111 (2014)Google Scholar
  10. 10.
    Huang, Z., Xu, W., Yu, K.: Bidirectional LSTM-CRF models for sequence tagging. Computing Research Repository, abs/1508.01991 (2015)Google Scholar
  11. 11.
    Ma, X., Hovy, E.: End-to-end sequence labeling via bi-directional LSTM-CNNs-CRF (2016)Google Scholar
  12. 12.
    Du, J., Gui, L., Xu, R.: Extracting opinion expression with neural attention. In: Li, Y., Xiang, G., Lin, H., Wang, M. (eds.) SMP 2016. CCIS, vol. 669, pp. 151–161. Springer, Singapore (2016).  https://doi.org/10.1007/978-981-10-2993-6_13CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Zhongming Han
    • 1
    • 2
    Email author
  • Xin Jiang
    • 1
  • Mengqi Li
    • 1
  • Mengmei Zhang
    • 1
  • Dagao Duan
    • 1
  1. 1.School of Computer and Information EngineeringBeijing Technology and Business UniversityBeijingChina
  2. 2.Beijing Key Laboratory of Big Data Technology for Food SafetyBeijingChina

Personalised recommendations