Spam Reviews and Spammer Community Detection using Machine Learning Algorithms

Authors

  • Nishigandha Rananaware  Department of Computer Engineering, NESGI, Pune, India
  • Shweta More  Department of Computer Engineering, NESGI, Pune, India
  • Prajakta Jagtap  Department of Computer Engineering, NESGI, Pune, India
  • Anuja Kumbharkar  Department of Computer Engineering, NESGI, Pune, India
  • A. C. Jadhav  Assistant Professor, Department of Computer Engineering, NESGI, Pune, India

Keywords:

CNN, spam reviews, machine learning, social network

Abstract

Online reviews and feedback of a product plays a vital role in human tendency to purchase those products. To affect the product sale spammer generates fake reviews on online social media platform. To identify spam reviews and spammer communities is the area of interest of this research work. In literature work, various spam detection techniques are proposed based on Review-Behavioral (RB) Based features, Review-Linguistic (RL) Based Features, User-Behavioral (UB) Based Features are explained but none of the technique provide a simultaneous study of these features and weighting of the features along with finding the relationship among the spam users. The proposed work generates a hybrid feature selection method which merge linguistic based features and behavioral features along with NLP processing and sentiment analysis. Also deep learning classification is used. The results show 91 % accuracy for detecting spam reviews.

References

  1. Saeedreza Shehnepoor, Mostafa Salehi*, Reza Farahbakhsh, Noel Crespi NetSpam:a Network-based Spam Detection Framework for Reviews in Online Social Media IEEE Transactions on Information Forensics and Security 2017.
  2. J. Donfro, A whopping 20 percent of yelp reviews are fake.
  3. M. Ott, C. Cardie, and J. T. Hancock. Estimating the prevalence of deception in online review communities. In ACM WWW, 2012.
  4. M. Ott, Y. Choi, C. Cardie, and J. T. Hancock. Finding deceptive opinion spam by any stretch of the imagination.In ACL, 2011.
  5. Ch. Xu and J. Zhang. Combating product review spam campaigns via multiple heterogeneous pairwise features. SIAM International Conference on Data Mining, 2014.
  6. N. Jindal and B. Liu. Opinion spam and analysis. In WSDM, 2008.
  7. F. Li, M. Huang, Y. Yang, and X. Zhu. Learning to identify review spam. Proceedings of the 22nd International Joint Conference on Artificial Intelligence; IJCAI, 2011.
  8. G. Fei, A. Mukherjee, B. Liu, M. Hsu, M. Castellanos, and R. Ghosh. Exploiting burstiness in reviews for review spammer detection. In ICWSM, 2013.
  9. Choo E., Yu T., Chi M. (2015) Detecting Opinion Spammer Groups Through Community Discovery and Sentiment Analysis. In: Samarati P. (eds) Data and Applications Security and Privacy XXIX. DBSec 2015. Lecture Notes in Computer Science, vol 9149. Springer, Cham.
  10. H. Li, Z. Chen, B. Liu, X. Wei, and J. Shao. Spotting fake reviews via collective PU learning. In ICDM, 2014.
  11. N. Jindal, B. Liu, and E.-P. Lim. Finding unusual review patterns using unexpected rules. In ACM CIKM, 2012.
  12. F. Li, M. Huang, Y. Yang, and X. Zhu. Learning to identify review spam. Proceedings of the 22nd International Joint Conference on Artificial Intelligence; IJCAI, 2011.
  13. S. Feng, R. Banerjee and Y. Choi. Syntactic stylometry for deception detection. Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Short Papers; ACL, 2012.
  14. Jillian D’Onfro, ?Google Maps spam fighters,? CNBC, 2018. Online]. Available: https://www.cnbc.com/2018/04/13/googlemaps-spam-fighters.html. Accessed: 24-May-2018]

Downloads

Published

2021-06-30

Issue

Section

Research Articles

How to Cite

[1]
Nishigandha Rananaware, Shweta More, Prajakta Jagtap, Anuja Kumbharkar, A. C. Jadhav, " Spam Reviews and Spammer Community Detection using Machine Learning Algorithms, International Journal of Scientific Research in Science, Engineering and Technology(IJSRSET), Print ISSN : 2395-1990, Online ISSN : 2394-4099, Volume 8, Issue 3, pp.444-449, May-June-2021.