Advertisement

Cross-Domain Text Sentiment Classification Based on Wasserstein Distance

  • Guoyong Cai
  • Qiang LinEmail author
  • Nannan Chen
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 895)

Abstract

Text sentiment analysis is mainly to detect the sentiment polarity implicit in text data. Most existing supervised learning algorithms are difficult to solve the domain adaptation problem in text sentiment analysis. The key of cross-domain text sentiment analysis is how to extract the domain shared features of different domains in the deep feature space. The proposed method uses denosing autoencoder to extract the deeper shared features with better robustness. In addition, Wasserstein distance-based domain adversarial and orthogonal constraints are combined for better extracting the deep shared features of the different domain. Finally, the deep shared features are used for cross domain sentiment classification. The experimental results on the real data sets show that the proposed method can better adapt to domain differences and achieve higher accuracy.

Keywords

Cross-domain Wasserstein distance Domain adversarial Text sentiment analysis 

References

  1. 1.
    Tan, S., Cheng, X., Wang, Y., Xu, H.: Adapting naive bayes to domain adaptation for sentiment analysis. In: European Conference on Information Retrieval, pp. 337–349. Springer, Heidelberg (2009)Google Scholar
  2. 2.
    Pan, S.J., Ni, X., Sun, J.-T., Yang, Q., Chen, Z.: Cross-domain sentiment classification via spectral feature alignment. In: Proceedings of the 19th International Conference on World Wide Web, pp. 751–760. ACM (2010)Google Scholar
  3. 3.
    Pan, W., Zhong, E., Yang, Q.: Transfer learning for text mining. In: Mining Text Data, pp. 223–257. Springer, Boston (2012)Google Scholar
  4. 4.
    Glorot, X., Bordes, A., Bengio, Y.: Domain adaptation for large-scale sentiment classification: a deep learning approach. In: Proceedings of the 28th International Conference on Machine Learning (ICML-11), pp. 513–520 (2011)Google Scholar
  5. 5.
    Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672–2680 (2014)Google Scholar
  6. 6.
    Ajakan, H., Germain, P., Larochelle, H., Laviolette, F., Marchand, M.: Domain-adversarial neural networks. arXiv preprint arXiv:1412.4446 (2014)
  7. 7.
    Arjovsky, M., Bottou, L.: Towards principled methods for training generative adversarial networks. arXiv preprint arXiv:1701.04862 (2017)
  8. 8.
    Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein generative adversarial networks. In: International Conference on Machine Learning, pp. 214–223 (2017)Google Scholar
  9. 9.
    Bousmalis, K., Trigeorgis, G., Silberman, N., Krishnan, D., Erhan, D.: Domain separation networks. In: Advances in Neural Information Processing Systems, pp. 343–351 (2016)Google Scholar
  10. 10.
    Salzmann, M., Ek, C.H., Urtasun, R., Darrell, T.: Factorized orthogonal latent spaces. In: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, pp. 701–708 (2010)Google Scholar
  11. 11.
    Heinonen, J.: Lectures on Lipschitz analysis. No. 100. University of Jyväskylä (2005)Google Scholar
  12. 12.
    Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., Courville, A.C.: Improved training of Wasserstein GANs. In: Advances in Neural Information Processing Systems, pp. 5767–5777 (2017)Google Scholar
  13. 13.
    Ganin, Y., Lempitsky, V.: Unsupervised domain adaptation by backpropagation. arXiv preprint arXiv:1409.7495 (2014)
  14. 14.
    Ruder, S.: An overview of gradient descent optimization algorithms. arXiv preprint arXiv:1609.04747 (2016)
  15. 15.
    Chen, M., Xu, Z., Weinberger, K., Sha, F.: Marginalized denoising autoencoders for domain adaptation. arXiv preprint arXiv:1206.4683 (2012)
  16. 16.
    van der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9, 2579–2605 (2008)zbMATHGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Guangxi Key Lab of Trusted SoftwareGuilin University of Electronic TechnologyGuilinChina

Personalised recommendations