Improving the Efficiency in Identification of Sentiments of COVID Patients over Online Social Networks using Novel Naive Bayes Algorithm Comparing Random Forest Algorithm

Abstract

Aim: The main aim of this research work is to predict the efficiency to recognize emotions of covid patients over social media by comparing novel Naive Bayes algorithm and Random Forest algorithm. Materials and Methods: Naive Bayes algorithm with sample size = 10 and Random Forest algorithm with sample size = 10 were evaluated many times to predict the efficiency percentage with confidence interval of 95% and G-power (Value=0.8). Results and Discussions: Naive Bayes algorithm has proven better efficiency (54%) when compared to Random Forest efficiency (25%). The results achieved with significance value p=0.776 (p>0.05) shows that two groups are statistically insignificant. Conclusion: Naive Bayes algorithm performed significantly better than the Random Forest algorithm.