Year
2023
Category
Project
Product Duration
3 Days
The analysis includes data preprocessing, feature engineering, and sentiment classification. The data is cleaned and tokenized, and features are extracted using TF-IDF vectorization. A machine learning model is trained on the preprocessed data to classify reviews as positive or negative.
We use a Random Forest model for sentiment classification. The trained model is saved and can be used for making predictions on new data.
The model's performance is evaluated using metrics such as accuracy, precision, recall, and F1-score. Details of the evaluation can be found in the .pynb file.
The dataset used for this project consists of IMDb movie reviews.
