Classify the Sentiments of email Contents using Novel Bidirectional Encoder Representation for Transformation over Naïve Bayes Algorithm
DOI:
https://doi.org/10.47750/pnr.2022.13.S04.036Keywords:
Novel BERT, Naïve Bayes Algorithm, Sentiment analysis, email, Spam Detection, Enron email dataset.Abstract
Aim: The aim of the study is to detect sentiment analysis from the good ones and improve the false positivity rate by using the proposed Novel Bidirectional Encoder Representation for Transformation (NBERT) over Naïve Bayes Algorithm.
Materials and Methods: Sample groups that are considered in the project can be classified into two, one for NBERT over Naïve Bayes Algorithm, which are tested using 0.80 for G-power to determine the sample size is 20 and for t-test analysis. Enron email content dataset that data collected from email.
Results: The automatic feature selection of NBERT algorithm splits the data with best fit, which has an average accuracy of 87%, which by far seems to be better than the Traditional Feature Extraction Method of Naïve Bayes Algorithm which gives 76%.The significance is around 0.0267 (p<0.05) and therefore there is a statistically insignificant difference among the study group.
Conclusion: NovelBERT seems to be better in finding the Sentiment in enron email dataset over the Naïve Bayes Algorithm.
