Hierarchical Adversarial Training for Multi-domain Adaptive Sentiment Analysis

  • Zhao XuEmail author
  • Lorenzo von Ritter
  • Giuseppe Serra
Part of the Studies in Computational Intelligence book series (SCI, volume 880)


Extracting useful insights with sentiment analysis is of increasing importance due to the growing availability of user-generated content. Sentiment analysis usually involves multiple different domains, and the labeled data is often difficult to obtain. In this paper we propose a hierarchical adversarial neural network (HANN) for adaptive sentiment analysis. Unlike most existing deep learning based methods, the proposed method HANN is able to share information between multiple domains bidirectionally, not just transfers information from source domain to target domain in one direction only. In particular, the HANN method is inspired by the ideas of hierarchical Bayesian modeling and generative adversarial networks. We introduce each domain a distinct encoder to model the domain-specific distribution of the latent features. The learning procedures on different domains are coupled by a discriminator network to propagate the information, which can be viewed as adversarial networks in a supervised context by forcing the discriminator to identify domain labels. The proposed method HANN not only captures the distinct properties of each domain, but also shares common information across multiple domains. We demonstrate the superior performance of our method on real data including the Amazon review dataset and the Sanders Twitter sentiment dataset.



This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 766186.


  1. 1.
    Blitzer, J., Dredze, M., Pereira, F.: Biographies, bollywood, boomboxes and blenders: domain adaptation for sentiment classification. In: Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics, pp. 440–447 (2007)Google Scholar
  2. 2.
    Courty, N., Flamary, R., Habrard, A., Rakotomamonjy, A.: Joint distribution optimal transportation for domain adaptation. In: NIPS, vol. 30 (2017)Google Scholar
  3. 3.
    Dai, A.M., Le, Q.V.: Semi-supervised sequence learning. In: Advances in Neural Information Processing Systems, vol. 28 (2015)Google Scholar
  4. 4.
    Erhan, D., Bengio, Y., Courville, A., Manzagol, P.A., Vincent, P., Bengio, S.: Why does unsupervised pre-training help deep learning? JMLR 11, 625–660 (2010)MathSciNetzbMATHGoogle Scholar
  5. 5.
    Evgeniou, T., Pontil, M.: Regularized multitask learning. In: Proceedings of the 10th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 109–117 (2004)Google Scholar
  6. 6.
    Fasano, G., Franceschini, A.: A multidimensional version of the kolmogorov-smirnov test. Mon. Notices R. Astron. Soc. 225, 155–170 (1987)CrossRefGoogle Scholar
  7. 7.
    Ganin, Y., Ustinova, E., Ajakan, H., Germain, P., Larochelle, H., Laviolette, F., Marchand, M., Lempitsky, V.: Domain-adversarial training of neural networks. J. Mach. Learn. Res. 17(59), 1–35 (2016)MathSciNetzbMATHGoogle Scholar
  8. 8.
    Gers, F.A., Schmidhuber, J., Cummins, F.: Learning to forget: continual prediction with lstm. Neural Comput. 12(10), 2451–2471 (2000)CrossRefGoogle Scholar
  9. 9.
    Glorot, X., Bordes, A., Bengio, Y.: Domain adaptation for large-scale sentiment classification: a deep learning approach. In: ICMLs (2011)Google Scholar
  10. 10.
    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, vol. 27 (2014)Google Scholar
  11. 11.
    Graves, A.: Supervised Sequence Labelling with Recurrent Neural Networks. Studies in Computational Intelligence. Springer, Berlin (2012)Google Scholar
  12. 12.
    Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)CrossRefGoogle Scholar
  13. 13.
    Le, Q.V., Mikolov, T.: Distributed representations of sentences and documents. In: ICML, pp. 1188–1196 (2014)Google Scholar
  14. 14.
    Li, S., Zong, C.: Multi-domain sentiment classification. In: ACL:HLT, pp. 257–260 (2008)Google Scholar
  15. 15.
    Li, S.S., Huang, C.R., Zong, C.Q.: Multi-domain sentiment classification with classifier combination. J. Comput. Sci. Technol. 26(1), 25–33 (2011)CrossRefGoogle Scholar
  16. 16.
    Li, Z., Zhang, Y., Wei, Y., Wu, Y., Yang, Q.: End-to-end adversarial memory network for cross-domain sentiment classification. In: Proceedings of the 26th International Joint Conference on Artificial Intelligence, pp. 2237–2243 (2017)Google Scholar
  17. 17.
    Liu, B.: Sentiment Analysis and Opinion Mining. Morgan & Claypool Publishers (2012)Google Scholar
  18. 18.
    Liu J, Ji S, Ye J (2009) Multi-task feature learning via efficient l2, 1-norm minimization. In: UAI, pp. 339–348Google Scholar
  19. 19.
    Long, M., Wang, J., Cao, Y., Sun, J., Yu, P.: Deep learning of transferable representation for scalable domain adaptation. IEEE Trans. Knowl. Data Eng. 28(8), 2027–2040 (2016)CrossRefGoogle Scholar
  20. 20.
    van der Maaten, L.J.P., Hinton, G.E.: Visualizing high-dimensional data using t-sne. J. Mach. Learn. Res. 9, 2579–2605 (2008)zbMATHGoogle Scholar
  21. 21.
    Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. Adv. Neural Inf. Process. Syst. 26, 3111–3119 (2013)Google Scholar
  22. 22.
    Odena, A.: Semi-supervised learning with generative adversarial networks. In: Data Efficient Machine Learning Workshop at ICML 2016 (2016)Google Scholar
  23. 23.
    Pang, B., Lee, L.: Opinion mining and sentiment analysis. Found. Trends Inf. Retr. 2(1–2), 1–135 (2008)CrossRefGoogle Scholar
  24. 24.
    Pennington, J., Socher, R., Manning, C.: Glove: global vectors for word representation. In: EMNLP, pp. 1532–1543 (2014)Google Scholar
  25. 25.
    Socher, R., Perelygin, A., Wu, J.Y., Chuang, J., Manning, C.D., Ng, A., Potts, C.: Recursive deep models for semantic compositionality over a sentiment treebank. In: EMNLP, pp. 1631–1642 (2013)Google Scholar
  26. 26.
    Sutskever, I.: Training recurrent neural networks. Ph.D. thesis, University of Toronto (2013)Google Scholar
  27. 27.
    Wu, F., Huang, Y.: Collaborative multi-domain sentiment classification. In: IEEE International Conference on Data Mining, pp. 459–468 (2015)Google Scholar
  28. 28.
    Zhao, H., Zhang, S., Wu, G., Costeira, J., Moura, J., Gordon, G.: Multiple source domain adaptation with adversarial training of neural networks (2017)Google Scholar
  29. 29.
    Zhou, J., Chen, J., Ye, J.: MALSAR: Multi-tAsk Learning via Structural Regularization. Arizona State University (2011)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.NEC Laboratories EuropeHeidelbergGermany
  2. 2.Technical University of MunichGarchingGermany
  3. 3.University of BirminghamBirminghamUK

Personalised recommendations