A Comparative Analysis of Classical Machine Learning and Deep Learning Approaches for Sentiment Classification on IMDb Movie Reviews

TL;DR

This study compares classical machine learning and deep learning methods for sentiment analysis on IMDb reviews, finding classical models like SVM outperform deep learning in accuracy.

Contribution

It provides a comprehensive comparison showing classical ML with TF-IDF can outperform deep learning models like BiLSTM with attention on this task.

Findings

SVM achieved the highest accuracy of 0.8530.

BiLSTM with Attention improved over standard BiLSTM.

Classical ML remains competitive with deep learning under limited resources.

Abstract

This paper presents a comparative study of classical machine learning and deep learning methods for sentiment classification on the IMDb movie reviews dataset. The machine learning pipeline uses TF-IDF features and PyCaret AutoML to evaluate Logistic Regression, Na\"ive Bayes, and Support Vector Machine, while the deep learning pipeline implements BiLSTM and BiLSTM with an attention mechanism. Experimental results show that classical machine learning, especially SVM, achieves the best performance with an accuracy of 0.8530, outperforming the deep learning models in this study. The BiLSTM with Attention model improves over the standard BiLSTM and reaches an accuracy of 0.706, indicating better contextual modeling. The paper concludes that although deep learning can capture sequential dependencies, classical machine learning remains a strong baseline when combined with effective feature engineering such as TF-IDF, particularly under limited data and computational resources.