Authors : T. Muralidharan, V. Saishanmuga Raja and S.P. Rajagopalan
Abstract: In the most recent couple of years as internet utilization turns into the principle supply route of the life’s every day exercises, the issue of spam turns out to be intense for web group. Spam pages frame a genuine risk for a wide range of clients. This risk demonstrated to advance constantly with no piece of information to lessen. Diverse types of spam saw an emotional increment in both size and negative effect. A lot of e-mails and website pages are considered spam either in Simple Mail Transfer Protocol (SMTP) or web crawlers. Numerous specialized strategies were proposed to approach the issue of spam. We propose a Hybrid Extensive Machine Learning Algorithm (HEMLA) for detection and classification of that offers weight to the data nourished by clients and thinks about the presence of some space particular components. Hybrid extensive machine learning algorithm is a combination of many learning algorithms like conjugate gradient, resilient back-propagation and levenberg-marquardt algorithms. The outcomes demonstrate that the hybrid extensive machine learning algorithm overcomes the traditional web filtering methods as far as reducing the false positives and the false negatives and increasing the accuracy.
T. Muralidharan, V. Saishanmuga Raja and S.P. Rajagopalan, 2017. Web Spam Detection and Classification using Hybrid Extensive Machine Learning Algorithm (HEMLA) for Domain Specific Features. Asian Journal of Information Technology, 16: 632-638.