Comparative Analysis of the Bernoulli and Multinomial Naive Bayes Classifiers for Text Classification in Machine Learning

The purpose of the report is a comparative analysis of the Bernoulli and Multinomial Naive Bayes classifiers in text classification for machine learning. The conducted research demonstrates that when classifying English user comments, the accuracy and precision of the Multinomial Naive Bayes classifier are higher than those of the Bernoulli Naive Bayes classifier, with the difference increasing with the volume of data. Both the Bernoulli and Multinomial Naive Bayes classifiers have identified a higher percentage of negative comments as belonging to their respective classes and a lower percentage of positive comments as belonging to their respective classes when classifying English user opinions. The Multinomial Naive Bayes classifier has higher values for the recall parameter of positive comments compared to the Bernoulli Naive Bayes classifier, whereas the Bernoulli Naive Bayes classifier has higher values for the recall parameter of negative comments compared to the Multinomial Naive Bayes classifier.