Predicting the Accuracy of Fractionation of Patron's Activities in Online Social Networks Using Novel K-Means Clustering Algorithm Comparing with Agglomerative Hierarchical Clustering Algorithm

Aim: This research compares a novel K-means clustering algorithm with an agglomerative hierarchical clustering algorithm for its ability to predict user behaviour in online social networks with a high degree of accuracy. Materials and methods: The accuracy percentage was predicted using a 95% confidence interval, a G power (value = 0.8), and an evaluation of the Novel K-Means clustering method with a sample size =10 and the Agglomerative hierarchical clustering algorithm with a sample size =10. Results: The findings shows that the Novel K-Means clustering method Agglomerative hierarchical clustering algorithm (78.81%) in terms of accuracy. Two Algorithms were found to be statistically significant, with a p value of 0.001 (p < 0.05). Conclusion: It was demonstrated that the Agglomerative hierarchical clustering approach performed inferior to the Novel K-Means clustering strategy.