This project focuses on building a Sentiment Analysis pipeline that classifies user-generated text (such as reviews or comments) as Positive, Negative, or Neutral using Natural Language Processing (NLP) techniques and machine learning.
- 📊 Text Preprocessing: Cleaning, tokenizing, stopword removal
- 🤖 Model Training: Logistic Regression
- 📈 Evaluation: Accuracy, Precision, Recall, F1-Score, Confusion Matrix
- 🗂️ Dataset: Public dataset
- Real-time sentiment prediction
- Clean and modular code structure
- Model performance comparison
- Custom text input support for user testing
- Language: Python
- Libraries: NLTK, Scikit-learn, Pandas, NumPy, Seaborn
Made with ❤️ by Arnav Tomar
- 📧 arnavtomar257@gmail.com
- 🌐 Portfolio Website
- 🐱 GitHub: @ArnavTomar