Advertisement

A Data Preprocessing Method to Classify and Summarize Aspect-Based Opinions Using Deep Learning

  • Duy Nguyen NgocEmail author
  • Tuoi Phan Thi
  • Phuc Do
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11431)

Abstract

Opinion summarization is based on aspect analyses of products, events or topics, which is a very interesting topic in natural language processing. Opinions are often expressed in various different ways in regards to objects. Therefore, it is important to express the characteristics of a product, event or topic in a final summary compiled by an automatic summarizing system. This paper proposes a method for conducting data preprocessing on the sentence level of a text using Convolutional Neural Networks. The corpus includes Vietnamese opinions on cars collected from social networking sites, forums, online newspapers and the websites of automobile dealers. The data processing phase will standardize terms for aspects that occur in opinion expressing aspects of the product. These aspects are used by manufacturers. Similarly, the standardization will be performed for both positive and negative terms used in opinions. The sentiment terms in the opinions will be replaced by standardized sentiment terms expressing the same sentiment polarities as those being replaced. This standardization is performed with the support of a semantic and sentiment ontology which has a tree hierarchy in the case of cars. This ontology ensures that the semantics and sentiment of the original opinion are not changed. The experimental results of the paper show that the proposed method gives better results than using no data preprocessing method for deep learning.

Keywords

Corpus Deep learning Classification CNN Convolution Neural Network Sentiment Summarization 

Notes

Acknowledgments

This paper was supported by research project TNCS_KHMT_2017_06, funded by the Ho Chi Minh City University of Technology, VNU-HCM.

References

  1. 1.
    Li, Q., Jin, Z., Wang, C., Zeng, D.D.: Mining opinion summarizations using convolutional neural networks in Chinese microblogging systems. Knowl.-Based Syst. 107, 289–300 (2016)CrossRefGoogle Scholar
  2. 2.
    Wu, H., Gu, Y., Sun, S., Gu, X.: Aspect-based opinion summarization with convolutional neural networks. In: International Joint Conference Neural Networks, IJCNN, pp. 3157–3163. IEEE (2016)Google Scholar
  3. 3.
    Dhanush, D., Thakur, A.K., Diwakar, N.P.: Aspect-based sentiment summarization with deep neural networks. Int. J. Eng. Res. Technol. 5(5), 371–375 (2016)Google Scholar
  4. 4.
    Thien, K.T., Tuoi, T.P.: Computing sentiment scores of verb phrases for Vietnamese. In: Proceedings of the Conference on Computational Linguistics and Speech Processing, pp. 204–213. ROCLING (2016)Google Scholar
  5. 5.
    Lin, C.Y.: Rouge: a package for automatic evaluation of summaries. In: Proceedings of the Workshop on Text Summarization Branches Out, pp. 74–81 (2004)Google Scholar
  6. 6.
    Xu, L., Lin, J., Wang, L., Yin, C., Wang, J.: Deep convolutional neural network based approach for aspect-based sentiment analysis. Adv. Sci. Technol. Lett. 143, 199–204 (2017)CrossRefGoogle Scholar
  7. 7.
    Kim, Y.: Convolutional neural networks for sentence classification. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, EMNLP, pp. 1746–1751 (2014)Google Scholar
  8. 8.
    Hu, M., Liu, B.: Mining opinion features in customer reviews. Assoc. Adv. Artif. Intell. 4(4), 755–760 (2004)Google Scholar
  9. 9.
    Liang, L.C., Hoar, H.W., Hoang, L.C., Chi, L.G., Emery, J.: Movie rating and review summarization in mobile environment. IEEE Trans. Syst. Man Cybern.-Part C: Appl. Rev. 42, 397–406 (2012)CrossRefGoogle Scholar
  10. 10.
    Xin, R.: word2vec parameter learning explained, in arXiv preprint arXiv:1411.2738 (2016)
  11. 11.
    Liao, C., Wang, J., Yu, R., Sato, K., Cheng, Z.: CNN for situations understanding based on sentiment analysis of Twitter data. Procedia Comput. Sci. 111, 376–381 (2017)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Ho Chi Minh City University of TechnologyVNU-HCMHo Chi Minh CityVietnam
  2. 2.Posts and Telecommunications Institute of TechnologyHo Chi Minh CityVietnam
  3. 3.University of Information TechnologyVNU-HCMHo Chi Minh CityVietnam

Personalised recommendations