--- # 💬 Sentiment Analysis using NLP

📌 Project Overview

This project is a Sentiment Analysis Web Application built using Natural Language Processing (NLP) and Machine Learning. It classifies user input text into sentiments such as Positive, Negative, or Neutral.

The application uses TF-IDF Vectorization for feature extraction and a Random Forest Classifier for prediction. A simple and interactive Streamlit UI allows users to test sentiment in real-time.

---

🚀 Features

• ✅ Text preprocessing using NLP techniques
• ✅ TF-IDF feature extraction
• ✅ Machine Learning model (Random Forest)
• ✅ Real-time sentiment prediction
• ✅ Interactive Streamlit web interface
• ✅ Clean and user-friendly UI

---

🛠️ Tech Stack

• Programming Language: Python

• Libraries:

  • pandas
  • numpy
  • nltk
  • scikit-learn
  • matplotlib
  • streamlit

---

📂 Project Structure

Sentiment-Analysis-NLP/
│── app.py
│── dataset.csv
│── requirements.txt
│── README.md

---

⚙️ Installation & Setup

1️⃣ Clone the Repository

git clone https://github.com/selvan-01/Sentiment-Analysis-NLP.git
cd Sentiment-Analysis-NLP

2️⃣ Install Dependencies

pip install -r requirements.txt

3️⃣ Run the Application

streamlit run app.py

---

📊 How It Works

1. Text data is cleaned using regex and stopword removal
2. TF-IDF converts text into numerical vectors
3. Random Forest model is trained on the dataset
4. User input is processed and predicted in real-time

---

📸 Example

Input:

I love this product! It's amazing 😍

Output:

Positive Sentiment 😊

---

🔗 Project Links

• 💼 LinkedIn: https://www.linkedin.com/in/senthamil45
• 🌍 Portfolio: https://senthamill.vercel.app/
• 💻 GitHub: https://github.com/selvan-01

---

📈 Future Improvements

• 🔥 Add Deep Learning (LSTM / BERT)
• 📊 Display prediction confidence score
• 🌐 Deploy on Streamlit Cloud
• 🎨 Improve UI/UX with advanced styling

---

🙌 Acknowledgements

This project is built for learning and demonstrating NLP and Machine Learning concepts in real-world applications.

---

⭐ Support

If you like this project, consider giving it a ⭐ on GitHub!

---