Natural Language Processing of Movie Reviews to Detect the Sentiments using Novel Bidirectional Encoder Representation-BERT for Transformers over Support Vector Machine

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 Transformers- (Novel BERT) over Support Vector MachineSVM. Materials and Methods: Sample groups that are considered in the project can be classified into two, one for Novel BERT over SVM , which are tested using 0.80 for G-power to determine the sample size and for t-test analysis. 25000 IMDB movie reviews dataset that data collected from Twitter. Results: The automatic feature selection of the BERT algorithm splits the data with best fit, which has an average accuracy of 83.5%, which by far seems to be better than the SVM which gives average accuracy 75.3%.The significance is around 0.042 (p<0.05) and therefore there is a statistically insignificant difference among the study group. Conclusion: BERT seems to be better in finding the Sentiment in IMDB movie dataset over the SVM algorithm.