Analyzing Sentiment using IMDb Dataset

Text is the largest repository of human knowledge acquired over thousands of years. This knowledge will impart even more meaning if mined for deeper insights. Sentiment Analysis (SA) provides a traditional machine learning (ML) solution to this problem by putting Natural Language Processing (NLP) to work. In the proposed work, we have performed SA on the IMDb movie reviews dataset taken from Kaggle's Bag of Words meets Bag of Popcorn challenge to demonstrate how valuable insights can be drawn from a bulk of textual data collected from the internet. We derive these insights by applying four traditional ML algorithms namely, Naïve Bayes (NB), Logistic Regression (LR), Random Forest (RF), and Decision Tree (DT). Furthermore, results of these four algorithms were compared on the basis of six evaluation metrics - confusion matrix, accuracy, precision, recall, F1 measure, and Area Under Curve (AUC).