The Mechanism of Spam Comment Detection Using Count Vectorizer and Naive Bayes Machine Learning Algorithms in Python

Abstract

AbstractAim : The aim of this study is to predict Novel spam comments using Naive Bayes and SVM algorithms to improve the accuracy. Spamming is the process of posting unwanted and awkward comments on specific posts in any type of social sharing medium or video sharing medium. Materials and Methods : The Dataset used for training and testing of proposed text precision models is created using the comments of some popular videos from Youtube with 5 attributes and Sample size = 150. The framework that retrieves suitable data adapts SVM algorithm and compares it with Naive Bayes algorithm. Results and Discussion : The retrieval accuracy of SVM classifier is (96.72%) and Naive Bayes algorithm is (90.89%). There exists a statistical significant difference between SVM and Naive Bayes with (p<0.05) Conclusion : The work has confirmed that the efficiency of the support vector machine algorithm has given more accuracy when compared to the Naive Bayes machine learning algorithm.