Sentiment-Analysis-NLP

This project involves building a sentiment analysis model for an e-commerce platform. The goal is to predict the binary rating (positive or negative) of product reviews based on their text data. The model uses machine learning techniques to classify reviews and provides a submission-ready CSV file for evaluation.

1. Text Preprocessing: Combines Review_Title and Review into a single feature for better context.
2. Modeling: Implements a Logistic Regression classifier with TF-IDF vectorization.
3. Evaluation: Achieved an F1-Score of 0.987 and an accuracy of 98% on the validation set.
4. Prediction: Generates predictions for the test dataset and prepares a submission file.

train.csv: Training dataset containing reviews and binary ratings. test.csv: Test dataset with reviews for which ratings need to be predicted. sample_submission.csv: Template for the submission file. final_predicted_ratings.csv: Output file with predicted ratings for the test set. model_code.ipynb: Jupyter Notebook containing the code for preprocessing, training, and evaluation. README.md: Documentation for the project.

1. Clone the repository: git clone <repository_url>
2. Navigate to the project directory: cd sentiment-analysis
3. Install the required Python packages: pip install -r requirements.txt
4. Run the Jupyter Notebook to preprocess data, train the model, and generate predictions: jupyter notebook model_code.ipynb
5. Submit the generated final_predicted_ratings.csv file for evaluation.

1. Python
2. Pandas
3. Scikit-learn
4. TF-IDF Vectorization
5. Logistic Regression

Ensure the following packages are installed:

1. pandas
2. scikit-learn
3. jupyter
4. You can install them using: pip install pandas scikit-learn jupyter

Special thanks to the hackathon organizers for providing the dataset and the opportunity to showcase machine learning and natural language processing skills.