Call for Paper - January 2020 Edition
IJCA solicits original research papers for the January 2020 Edition. Last date of manuscript submission is December 20, 2019. Read More

Improved Social Network aided personalized Spam Filtering Approach using RBF Neural Network

Print
PDF
IJCA Proceedings on International Conference on Emerging Trends in Computing and Communication
© 2018 by IJCA Journal
ICETCC 2017 - Number 3
Year of Publication: 2018
Authors:
Shatabdi M. Bhalerao
Madhuri Dalal

Shatabdi M Bhalerao and Madhuri Dalal. Article: Improved Social Network aided personalized Spam Filtering Approach using RBF Neural Network. IJCA Proceedings on International Conference on Emerging Trends in Computing and Communication ICETCC 2017(3):23-26, June 2018. Full text available. BibTeX

@article{key:article,
	author = {Shatabdi M. Bhalerao and Madhuri Dalal},
	title = {Article: Improved Social Network aided personalized Spam Filtering Approach using RBF Neural Network},
	journal = {IJCA Proceedings on International Conference on Emerging Trends in Computing and Communication},
	year = {2018},
	volume = {ICETCC 2017},
	number = {3},
	pages = {23-26},
	month = {June},
	note = {Full text available}
}

Abstract

Currently the spam filtering technology is based on the naive Bayesian model. Because of the extremely complex semantic environment as well as naive Bayesian algorithms are easily deceiving; it is not very good at spam filtering. The recent method presented is SOcial network Aided Personalized and effective spam filter (SOAP) using Bayesian spam filtering technique. SOAP showing better results as compared to existing methods, but still it can be further improved in terms of accuracy, efficiency and complexity. In this paper we are presenting extension to SOAP method termed as ISOAP (Improved SOAP) by using RBF (Radial Basis Function) neural network rather than naïve Bayes method for spam filtering. Unlike previous spam filters that focus on parsing keywords or building blacklists, ISOAP exploits the social relationships among email correspondents and their (dis) interests to detect spam adaptively and automatically.

References

  • Haiying Shen and Ze Li, "Leveraging Social Networks for Effective Spam Filtering", IEEE
  • GFI Software, "Why Bayesian Filtering is the Most Effective Antispam Technology", http://www. gfi. com/whitepapers/Whybayesian-filtering. pdf,2011
  • M. Uemura and T. Tabata, "Design and Evaluation of a Bayesian-Filter-Based Image Spam Filtering Method", Proc. (ISA),pp. 46-51,2008.
  • X. Carreras, J. Salgado, "Boosting Trees for Anti-Spam Email Filtering", Proc. (RANLP),2001.
  • P. H, T. Scheffer, "Supervised Clustering of Streaming Data for Email Batch Detection", 2007.
  • [J. A. K. Suykens and J. Vandewalle, "Least Squares Support Vector Machine Classifiers", 1999.
  • S. J. Delany ,P. Cunningham, "An Assessment of Case-Based Reasoning for Spam Filtering",2005.
  • W. Zhao and Z. Zhang , "Email Classification Model Based on Rough Set Theory",2005.
  • J. S. Kong, P. O. Boykin, "Let Your Cyber Alter Ego Share Information and Manage Spam", 2005.
  • F. Zhou, Z Huang, "Approximate Object Location and Spam filtering on Peer-to-Peer Systems", 2003.
  • SPAMNET, http://www. cloudmark. com
  • P. O. Boykin, V. Roychowdhary, "Personal Email Networks: An Effective Anti-Spam Tool", 2004.
  • S. Garris, H. Yu, "Re: Reliable Email", NSDL, 2006.
  • S. Hameed, N. Sastry, "LENS: Leveraging Social Networking and Trust to Prevent Spam".
  • I. Rish, "An Empirical study of naïve Bayes classifier".
  • K. Jha, "Comparison of Naïve Bayes Classifier, Decision Tree and ANN for the purpose of spam detection".
  • Pragya B, S. Bagwari, "Comparison of Feed Forward Network and Radial Basis Function for Detecting and Recognition of license Plate", IJCA, May 2015.