Feed Forward Neural Network and K-Nearest Neighbour Based Comparative Accurate Social Media Spam Detection
Grandhi Sivadasu, Malaiyalathan Adimoolam · Advances in parallel computing · 2022
The aim of this work is to perform spam detection in social media using Feed Forward Neural Network (FFNN) algorithm and compare its accuracy with K-Nearest Neighbour (KNN) algorithm. The experiment was carried out and classification was performed using KNN algorithm (N=10) for spam detection in social media and the accuracy was compared with SVM algorithm (N=10). For this experiment, G power value was calculated as 80 % and alpha value was as 0.05 %. The value obtained in terms of accuracy was identified for KNN algorithm (95.2%) and for FFNN algorithm (98.2%) with significant value 0.276. It was conclude that the accuracy of detecting spam using the FFNN algorithm give the impression to be slightly better than the KNN algorithm.