Sentiment Analysis of Customer Reviews Using Robust Hierarchical Bidirectional Recurrent Neural Network

  • Arindam ChaudhuriEmail author
  • Soumya K. Ghosh
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 464)


With tremendous growth of online content, sentiment analysis of customer reviews has become an active research topic for machine learning community. However, due to variety of products being reviewed online traditional methods do not give desirable results. As number of reviews expand, it is essential to develop robust sentiment analysis model capable of extracting product aspects and determine sentiments adhering to various accuracy measures. Here, hierarchical bidirectional recurrent neural network (HBRNN) is developed in order to characterize sentiment specific aspects in review data available at DBS Text Mining Challenge. HBRNN predicts aspect sentiments vector at review level. HBRNN is optimized by fine tuning different network parameters and compared with methods like long short term memory (LSTM) and bidirectional LSTM (BLSTM). The methods are evaluated with highly skewed data. All models are evaluated using precision, recall and F1 scores. The results on experimental dataset indicate superiority of HBRNN over other techniques.


Semantic analysis Customer reviews RNN BRNN HBRNN 


  1. 1.
    Feldman, R.: Techniques and applications for sentiment analysis. Commun. ACM 56(4), 82–89 (2013)CrossRefGoogle Scholar
  2. 2.
    Li, M. X., Tan, C. H., Wei, K. K., Wang, K. L.: Where to place product review? An information search process perspective. In: 31st International Conference on Information Systems, Paper 60 (2010)Google Scholar
  3. 3.
    Liu, B.: Sentiment analysis and opinion mining. In: Synthesis Lectures on Human Language Technologies, vol. 16. Morgan and Claypool (2012)Google Scholar
  4. 4.
    Liu, B., Zhang, L.: A survey of opinion mining and sentiment analysis. In: Aggarwal, C.C., Zhai, C.X. (eds.) Mining Text Data, pp. 415–463. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  5. 5.
    Balahur, A., Hermida, J.M., Montoyo, A.: Detecting implicit expressions of emotion in text: a comparative analysis. Decis. Support Syst. 53, 742–753 (2012)CrossRefGoogle Scholar
  6. 6.
    Bickart, B., Schindler, R.M.: Internet Forums as Influential Sources of Consumer Information. J. Interact. Mark. 15(3), 31–40 (2001)CrossRefGoogle Scholar
  7. 7.
    Chen, Y., Xie, J.: Online consumer review: word-of-mouth as a new element of marketing communication mix. Manage. Sci. 54(3), 477–491 (2008)CrossRefGoogle Scholar
  8. 8.
    Hu, M., Liu, B.: Mining opinion features in customer reviews. In: 19th National Conference on Artificial Intelligence, pp. 755–760. AAAI Press (2004)Google Scholar
  9. 9.
    Popescu, A.M., Etzioni, O.: Extracting product features and opinions from reviews. In: Conference on Empirical Methods in Natural Language Processing, Association for Computational Linguistics, pp. 339–346 (2005)Google Scholar
  10. 10.
    Wei, C.P., Chen, Y.M., Yang, C.S., Yang, C.C.: Understanding what concerns consumers: a semantic approach to product feature extraction from consumer reviews. IseB 8(2), 149–167 (2010)CrossRefGoogle Scholar
  11. 11.
    Yi, J., Nasukawa, T., Bunescu, R., Niblack, W.: Sentiment analyzer: extracting sentiments about a given topic using natural language processing techniques. In: 3rd IEEE International Conference on Data Mining, pp. 427–434 (2003)Google Scholar
  12. 12.
    Zhu, J., Wang, H., Zhu, M., Tsou, B.K., Ma, M.: Aspect based opinion polling from customer reviews. IEEE Trans. Affect. Comput. 2(1), 37–49 (2011)CrossRefGoogle Scholar
  13. 13.
  14. 14.
    Chaudhuri, A.: Semantic analysis of customer reviews with machine leaning methods. Technical Report, Samsung R & D Institute, Delhi, India (2015)Google Scholar
  15. 15.
    Heaton, J.: Deep Learning and Neural Networks. In: Artificial Intelligence for Humans, vol. 3. CreateSpace Independent Publishing Platform (2015)Google Scholar
  16. 16.
    Ahres, Y., Volk, N.: Entity level sentiment analysis for amazon web reviews. Final Year Project Report, Stanford University, California (2015)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  1. 1.Samsung R & D Institute DelhiNoidaIndia
  2. 2.Department of Computer Science EngineeringIndian Institute of TechnologyKharagpurIndia

Personalised recommendations