Sentiment classification holds significant importance in the field of nlp as it focuses on determining the sentiment polarity of text, namely positive, negative, or neutral. The widespread usage of IMDB as a platform for expressing opinions and emotions has made it a valuable source of data for sentiment classification. Here, we present a comparative analysis of diverse ML and DL approaches applied to sentiment classification using IMDB data. Specifically, we evaluate the performance of Bayesian classifier, Log. Regression, SVM, Recurrent Neural Systems (RNNS), and Transfer Learning with BERT. Through our experimentation, we find that while Bayesian classifier and Log. Regression exhibit reasonable accuracy in this task, SVM and RNNS surpass them, with Transfer Learning using BERT achieving the highest level of accuracy. This study offers valuable insights into the efficacy of different ML and DL techniques when applied to sentiment classification on IMDB data, serving as a valuable resource for both researchers and industry practitioners in this domain.