A Comparative Analysis of Classical Machine Learning and Deep Learning Approaches for Sentiment Classification on IMDb Movie Reviews
For practitioners working on sentiment analysis with limited data and resources, this study confirms that classical ML with TF-IDF can outperform deep learning, but the results are incremental and dataset-specific.
This paper compares classical ML (SVM, Logistic Regression, Naive Bayes with TF-IDF) and deep learning (BiLSTM, BiLSTM+Attention) on IMDb sentiment classification. SVM achieved the best accuracy of 0.8530, outperforming BiLSTM+Attention (0.706).
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, Naïve 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.