Semantic Graph Based Convolutional Neural Network for Spam e-mail Classification in Cybercrime Applications

Spam is characterized as unnecessary and garbage E-mails. Due to the increasing of unsolicited E-mails, it becoming more crucial for mail users utilize a trustworthy spam E-mail filter. The shortcomings classifier are defined by their inability manage large amounts relevant messages effectively detect messages. Numerous characteristics in classifications problematic. Given that selecting features one most often used successful techniques feature reduction, duty identification keyword content. As result, pointless yet potentially harm effciency would be removed. In this study, we present SGNNCNN (Semantic Graph Neural Network With CNN) solution tackle diffcult task identification. By projections E-mails onto graph using SGNN-CNN model classifications, technique transforms classification issue into challenge. There no need integrate word representation since produced from semantic network. On several open databases, technique's effectiveness evaluated. Some few public databases were experiments demonstrate high accuracy proposed approach classifying term classification, performance superior state-of-the-art deep learning-based methods.