Semi-supervised Learning with Ensemble Method for Online Deceptive Review Detection

Authors

  • Miss. Priyanka Shinde  Pune Institute of Computer Technology, Pune, Maharashtra, India
  • Prof. Hemlata Channe  Pune Institute of Computer Technology, Pune, Maharashtra, India

Keywords:

Opinion Spam, Multilabel and Multiclass, Ensemble of classifiers , Co-training, PU learning, EM algorithm

Abstract

Now-a-days not only organizers but users also prefer to give opinion after using any kind of resource. Opinion of user is very important for business. Because of opinion of actual user further consumers should think to use that resource. In Business, opinion review has great impact to economical bottom line. Unsurprisingly, opportunistic individuals or groups have attempted to abuse or manipulate online opinion reviews (e.g., spam reviews) so that they credit or degrade the target product. Because of this detecting deceptive and fake opinion reviews is a topic of ongoing research interest. In this paper semi-supervised learning approach with ensemble learning methods is used for finding out these spam reviews. Utility is demonstrated using a data set of online hotel booking websites.

References

  1. J. Rout, A. Dalmia, S. Bakshi, and S. Jena, “Revisiting semi-supervised learning for online deceptive review detection,”in Proc. 15th IEEE Int. Conf. Trust,Secur. Privacy Comput. and Internet of things, vol. 2, no. 1, pp. 15–25, 2017
  2. O. chappel,“ Semi-supervised learning,” https:// www. molgen. mpg. de / 3659531/ MITPress SemiSupervised- Learning.pdf, 2006
  3. F. Li, M. Huang, and Y. Y., “Learning to identify review spam,” Proc. 22nd International Joint Conference Artif. Intell. (IJAI), pp. 24–84, 2011.
  4. L.Zhou, Y. Sh, and D. Zhang, “A statistical language modeling approach to online deception detection,”IEEE Transaction on Knowledge and Data Engineering, vol. 20, no. 8, pp. 11–28, 2009.
  5. P. Mallapragada, R. Jin, A. Jain, and Y. Liu, “Semiboost: Boosting for semisupervised learning,” Tech. Rep. MSU-CSE, Michigan State University, pp. 7–197, 2007.
  6. H. Li, B. Liu, and A. S. J. Mukherjee, “Spotting fake reviews using positiveunlabeled learning,” Comput. Sistemas , IEEE International Conference,vol. 18, no. 3, pp. 46–74, 2011.
  7. A. Mukherjee, B. Liu, J. Wang, N. Glance, and N. Jindal, “Detecting group review spam,” Proceedings 20th International Conference in Companion World Wide Web, pp. 93–94, 2011.
  8. D. Hernndez and G. R., “Using PU-learning to detect deceptive opinion spam,”Proc. 4th Workshop Computer Approaches Subjectivity, Sentiment Social Media Anal., vol. 1, pp. 38–45, 2013.
  9.  Y. Ren and Y. Zhang, “Deceptive opinion spam detection using neural network,” Singapore University of Technology and Design, Singapore, pp. 11–28,2016.
  10.  Kaggle, “Kaggle,” http://www.kaggle.com
  11. Morgan and Claypool, “Sentiment analysis: mining opinions, sentiments, and emotions,” Cambridge University Press, pp. 1–8, 2015
  12. Z. Gyngyi, G. H., Y. Molina, and P. J., “Combating web spam with trustrank,”Proc. 13th Int. Conf. Very Large Data Bases (VLDB), IEEE International Conference, vol. 30, pp. 57–87, 2004.
  13. A. Ntoulas, M. Najork, M. Manasse, and F. D., “Detecting spam web pages through content analysis,” Proceedings in 15th International Conference World Wide Web (WWW), pp. 83–92, 2006
  14. H. Drucker, D. Wu, and V. Vapnik, “Support vector machines for spam categorization,” IEEE Transaction Neural Network, vol. 10, no. 5, pp. 10–54, 1999.
  15. W. Feng and G. Hirst, “Detecting deceptive opinions with prole compatibility,” Proceedings 6th IEEE International Conference on Natural Lang. Process(IJCNLP), pp. 33–83, 2013
  16. J. Lee and S. Yoo, “An elliptical boundary model for skin color detection,” Proc. of the 2002 International Conference on Imaging Science, Systems, and Technology, 2002
  17. K. Lau, Y. Li, and Y. Jing, “Toward a language modeling approach for consumer review spam detection,” Proc. IEEE 7th Int. Conf. e-Bus. Eng. (ICEBE),pp. 1–8, 2010.
  18. A. Mukherjee and V. Venkataraman, “What yelp fake review filter might be doing?” in Proc. 7th Int. AAAI Conf. Weblogs Social Media, pp. 409–418,2013.
  19. B. Liu and W. Lee, “Building text classifiers using positive and unlabeled examples,” ICDM-03, Melbourne Florida, pp. 19–22, 2003.
  20. Y. Dai and Y. Philip, “Partially supervised classification of text documents,”Proceedings of the Nineteenth International Conference on Machine Learning (ICML-2002),Sydney, pp. 387–394, 2002.
  21. W. Liu, Y. Li, D. Tao, and Y. Wang, “A general framework for co-training and its applications,”IEEE transaction on Neurocomputing, vol. 167, no. 10, pp.112–121, 2015.
  22. D. Fusilier, M. Montes-y Gmez, P. Rosso, and R. Cabrera, “Detecting positive and negative deceptive opinions using PU-learning,”Inf. Process. Manage.,vol. 51, no. 4, pp. 433–443, 2015.
  23. J. Peng, R. Choo, and H. Ashman, “Bit-level n-gram based forensic authorship analysis on social media: Identifying individuals from linguistic profiles,”J.Netw. Comput. Appl., vol. 70, pp. 171–182, 2016.

IInternational Journal of Scientific Research in Computer Science, Engineering and Information Technology

Downloads

Published

2018-07-30

Issue

Volume 3, Issue 6, July-August-2018

Section

Research Articles

License

Copyright (c) IJSRCSEIT

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

[1]
Miss. Priyanka Shinde, Prof. Hemlata Channe, " Semi-supervised Learning with Ensemble Method for Online Deceptive Review Detection" International Journal of Scientific Research in Computer Science, Engineering and Information Technology(IJSRCSEIT), ISSN : 2456-3307, Volume 3, Issue 6, pp.415-422, July-August-2018.