Features Extraction Based on Neural Network for Cross-Domain Sentiment Classification

  • Endong Zhu
  • Guoyan Huang
  • Biyun Mo
  • Qingyuan WuEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9645)


Sentiment analysis is important to develop marketing strategies, enhance sales and optimize supply chain for electronic commerce. Many supervised and unsupervised algorithms have been applied to build the sentiment analysis model, which assume that the distributions of the labeled and unlabeled data are identical. In this paper, we aim to deal with the issue of a classifier trained for use in one domain might not perform as well in a different one, especially when the distribution of the labeled data is different with that of the unlabeled data. To tackle this problem, we incorporate feature extraction methods into the neural network model for cross-domain sentiment classification. These methods are applied to simplify the structure of the neural network and improve the accuracy. Experiments on two real-world datasets validate the effectiveness of our methods for cross-domain sentiment classification.


Cross-domain sentiment classification Neural network Feature extraction Transfer learning 



This research has been substantially supported by a grant from the Soft Science Research Project of Guangdong Province (Grant No. 2014A030304013).


  1. 1.
    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 (2010)Google Scholar
  2. 2.
    Zhang, Y., Zhang, N., Si, L., Lu, Y., Wang, Q., Yuan, X.: Cross-domain and cross-category emotion tagging for comments of online news. In: Proceedings of the 37th International ACM SIGIR Conference, pp. 627–636 (2014)Google Scholar
  3. 3.
    Pang, B., Lee, L., Vaithyanathan, S.: Thumbs up? sentiment classification using machine learning techniques. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing, pp. 79–86 (2002)Google Scholar
  4. 4.
    Nigam, K., McCallum, A.K., Thrun, S., Mitchell, T.: Text classification from labeled and unlabeled documents using em. Mach. Learn. 39(2–3), 103–134 (2000)CrossRefzbMATHGoogle Scholar
  5. 5.
    Morchid, M., Dufour, R., Linares, G.: Topic-space based setup of a neural network for theme identification of highly imperfect transcriptions. In: IEEE Automatic Speech Recognition and Understanding Workshopp (2015)Google Scholar
  6. 6.
    Francesca, F., Zanzotto, F.M.: SVD feature selection for probabilistic taxonomy learning. In: Proceedings of the Workshop on Geometrical Models of Natural Language Semantics, pp. 66–73 (2009)Google Scholar
  7. 7.
    Dasgupta, A., Drineas, P., Harb, B., Josifovski, V., Mahoney. M.W.: Feature selection methods for text classification. In: Proceedings of the 13th ACM SIGKDD International Conference, pp. 230–239 (2007)Google Scholar
  8. 8.
    Rao, Y., Lei, J., Liu, W., Li, Q., Chen, M.: Building emotional dictionary for sentiment analysis of online news. World Wide Web J. 17, 723–742 (2014)CrossRefGoogle Scholar
  9. 9.
    Rao, Y., Li, Q., Liu, W., Wu, Q., Quan, X.: Affective topic model for social emotion detection. Neural Netw. 58, 29–37 (2014)CrossRefGoogle Scholar
  10. 10.
    Rao, Y., Li, Q., Mao, X., Liu, W.: Sentiment topic models for social emotion mining. Inf. Sci. 266, 90–100 (2014)CrossRefGoogle Scholar
  11. 11.
    Dai, W., Xue, G.-R., Yang, Q., Yu, Y.: Co-clustering based classification for out-of-domain documents. In: Proceedings of the 13th ACM SIGKDD International Conference, pp. 210–219 (2007)Google Scholar
  12. 12.
    Dhillon, I.S., Mallela, S., Modha, D.S.: Information-theoretic co-clustering. In: Proceedings of the 9th ACM SIGKDD International Conference, pp. 89–98 (2003)Google Scholar
  13. 13.
    Rao, Y.: Contextual sentiment topic model for adaptive social emotion classification. IEEE Intell. Syst. 31(1), 41–47 (2016)CrossRefGoogle Scholar
  14. 14.
    Strapparava, C., Mihalcea, R.: Semeval- task 14: affective text. In: Proceedings of the 4th International Workshop on Semantic Evaluations, pp. 70–74 (2007)Google Scholar
  15. 15.
    Hecht-Nielsen, R.: Theory of the backpropagation neural network. In: International Joint Conference on Neural Networks, pp. 593–605 (1989)Google Scholar
  16. 16.
    Kurkova, V., Kainen, P.C., Kreinovich, V.: Estimates of the number of hidden units and variation with respect to half-spaces. Neural Netw. 10(6), 1061–1068 (1997)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  • Endong Zhu
    • 1
  • Guoyan Huang
    • 1
  • Biyun Mo
    • 1
  • Qingyuan Wu
    • 2
    Email author
  1. 1.Sun Yat-sen UniversityGuangzhouChina
  2. 2.Beijing Normal UniversityZhuhaiChina

Personalised recommendations