Modeling Spammer Behavior: Na\"ive Bayes vs. Artificial Neural Networks

TL;DR

This paper compares Na"ive Bayes and Artificial Neural Networks for modeling spammer behavior, demonstrating that both methods achieve around 92% detection rate, outperforming keyword-based filters.

Contribution

It provides a comparative analysis of Na"ive Bayes and ANN for spam detection, highlighting their effectiveness in modeling evasive spammer tactics.

Findings

Both models achieve approximately 92% detection rate.

Models outperform traditional keyword-based filtering.

Both methods effectively capture spammer behavior patterns.

Abstract

Addressing the problem of spam emails in the Internet, this paper presents a comparative study on Na\"ive Bayes and Artificial Neural Networks (ANN) based modeling of spammer behavior. Keyword-based spam email filtering techniques fall short to model spammer behavior as the spammer constantly changes tactics to circumvent these filters. The evasive tactics that the spammer uses are themselves patterns that can be modeled to combat spam. It has been observed that both Na\"ive Bayes and ANN are best suitable for modeling spammer common patterns. Experimental results demonstrate that both of them achieve a promising detection rate of around 92%, which is considerably an improvement of performance compared to the keyword-based contemporary filtering approaches.