Web spam classification using supervised artificial neural network algorithms

TL;DR

This paper evaluates three supervised neural network algorithms—Conjugate Gradient, Resilient Backpropagation, and Levenberg-Marquardt—for classifying complex web spam patterns, aiming to improve efficiency and adaptability in spam detection.

Contribution

It introduces a comparative analysis of three neural network algorithms specifically applied to the challenging task of web spam classification, filling a research gap.

Findings

Resilient Backpropagation showed high accuracy.

Levenberg-Marquardt achieved fast convergence.

All algorithms demonstrated adaptability to complex spam patterns.

Abstract

Due to the rapid growth in technology employed by the spammers, there is a need of classifiers that are more efficient, generic and highly adaptive. Neural Network based technologies have high ability of adaption as well as generalization. As per our knowledge, very little work has been done in this field using neural network. We present this paper to fill this gap. This paper evaluates performance of three supervised learning algorithms of artificial neural network by creating classifiers for the complex problem of latest web spam pattern classification. These algorithms are Conjugate Gradient algorithm, Resilient Backpropagation learning, and Levenberg-Marquardt algorithm.