Poor Accuracy in Determining Erratic User Behavior in Social Media Networks Using KNN Algorithm Comparing SVM Algorithm

Abstract

The main aim of this research is to determine the erratic user behaviour over social media using machine learning classifiers by comparing Novel K-Nearest Neighbour algorithm and Support Vector Machine algorithm. Classification is performed using K-Nearest Neighbour with sample size (N=10) and Support Vector Machine sample size (N=10), and results were compared based on the accuracy of both algorithms. The KNN is used to determine the accuracy of erratic user behaviour with the help of social media network reviews with twitter data. The accuracy achieved for KNN is (95.30%) and SVM is (92.67%). The statistical significance between K-Nearest Neighbour & Support Vector Machine is (p=0.0094) where (p<0.05).K-Nearest Neighbour algorithm helps in determining with more accuracy in erratic user behaviour over social media networks, and here KNN algorithm shows better accuracy than SVM algorithm.