Sentiment Analysis System

A modern sentiment analysis system that combines Morphological Sentence Pattern (MSP) model with Convolutional Neural Networks (CNN) for improved accuracy and efficiency.

Features

• Real-time sentiment analysis
• MSP-based text preprocessing
• CNN-based sentiment classification
• Part-of-Speech (POS) tagging
• Batch text processing
• Modern web interface
• API documentation with Swagger UI

Tech Stack

Backend

• Python 3.11+
• FastAPI
• TensorFlow
• NLTK
• Pydantic v2
• Uvicorn

Frontend

• Next.js 14
• React 19
• TypeScript
• Tailwind CSS
• Shadcn UI
• Radix UI

Project Structure

sentiment-analysis/
├── backend/
│   ├── api/
│   │   ├── routes/
│   │   │   └── sentiment.py
│   │   └── main.py
│   ├── models/
│   │   └── neural_networks/
│   │       ├── cnn_model.py
│   │       └── msp_model.py
│   ├── services/
│   │   └── sentiment_service.py
│   ├── tests/
│   │   └── conftest.py
│   └── requirements.txt
├── frontend/
│   ├── app/
│   │   ├── page.tsx
│   │   └── layout.tsx
│   ├── components/
│   │   ├── ui/
│   │   └── features/
│   ├── lib/
│   │   └── api/
│   │       └── client.ts
│   └── package.json
└── docs/
    └── api/
        └── README.md

Getting Started

Backend Setup

1. Create and activate virtual environment:

   cd backend
   python3 -m venv .venv
   source .venv/bin/activate  # On Windows: .venv\Scripts\activate

2. Install dependencies:

   pip install -r requirements.txt

3. Start the server:

   uvicorn main:app --reload

The API will be available at http://localhost:8000 with Swagger documentation at http://localhost:8000/docs.

Frontend Setup

1. Install dependencies:

   cd frontend
   pnpm install

2. Start the development server:

   pnpm dev

The frontend will be available at http://localhost:3000.

Deployment

Vercel Deployment

This project is configured for deployment on Vercel with the following setup:

1. Frontend Deployment:

   • The frontend will be automatically deployed as a Next.js application
   • API routes are proxied to the backend

2. Backend Deployment:

   • The backend is deployed as serverless functions
   • Python 3.11 runtime is used

3. Environment Variables:

   • Set NEXT_PUBLIC_API_URL to your backend URL in Vercel dashboard
   • Update the backend URL in frontend/next.config.mjs after deployment

4. Deployment Steps:

   # Install Vercel CLI
   npm i -g vercel
   
   # Deploy to Vercel
   vercel
   
   # Follow the prompts and set up your project

5. Post-Deployment:

   • Update the backend URL in frontend/next.config.mjs with your actual backend domain
   • Set environment variables in Vercel dashboard
   • Redeploy if necessary

API Endpoints

• POST /api/analyze - Analyze single text
• POST /api/batch - Analyze multiple texts
• GET /health - Health check endpoint

Development

Backend Development

• Use Python 3.11 or higher
• Follow PEP 8 style guide
• Write unit tests for new features
• Update API documentation

Frontend Development

• Use TypeScript for type safety
• Follow component-based architecture
• Implement responsive design
• Add error handling

Testing

Backend Tests

cd backend
pytest

Frontend Tests

cd frontend
pnpm test

Contributing

1. Fork the repository
2. Create a feature branch
3. Commit your changes
4. Push to the branch
5. Create a Pull Request

License

MIT License - see LICENSE file for details

Authors

• K. Borad