Advanced AI-Powered Sentiment Analysis App

Overview

This application leverages Go and Python to provide an advanced sentiment analysis API. It integrates a pre-trained machine learning model from Hugging Face to analyze text sentiment (Positive, Negative, or Neutral) and calculates confidence levels. Additionally, the app extracts significant keywords from the input text.

---

Features

• ML-Based Sentiment Analysis: Utilizes a pre-trained DistilBERT model for accurate sentiment classification.
• Confidence Scoring: Computes a confidence level for the sentiment classification.
• Keyword Extraction: Extracts meaningful keywords from the input text.
• Hybrid Architecture: Combines the speed and concurrency of Go with the ML capabilities of Python.

---

Architecture

1. Go Backend:
   • Handles HTTP requests and response generation.
   • Sends text input to the Python ML service.
   • Extracts keywords using basic text processing.
2. Python ML Service:
   • Hosts the sentiment analysis model using the Hugging Face transformers library.
   • Processes text input and returns sentiment predictions to the Go backend.

---

Prerequisites

• Go: Version 1.18 or later.
• Python: Version 3.7 or later.
• Python Libraries:
  • flask
  • transformers

---

Set Up the Python ML Service

1. Navigate to the python_service directory:

   cd python_service

2. Install the required Python libraries:

   pip install -r requirements.txt

3. Start the ML service:

   python ml_service.py

   The service will run on port 5000.

Set Up the Go Backend

1. Navigate to the go_app directory:

   cd ../go_app

2. Run the Go application:

   go run main.go

   The server will start on port 8080.

---

API Endpoints

POST /predict

Analyzes the sentiment of the input text.

Request

• URL: http://localhost:8080/predict
• Method: POST
• Headers: Content-Type: application/json
• Body:

  {
    "text": "I love coding with Go and Python!"
  }

Response

• Example:

  {
    "text": "I love coding with Go and Python!",
    "sentiment": "POSITIVE",
    "confidence": 0.99,
    "keywords": ["love", "coding", "with", "Python"]
  }

---

How It Works

1. Python ML Service:
   • Receives the input text.
   • Processes the text using the DistilBERT sentiment analysis model.
   • Returns the sentiment and confidence levels.
2. Go Backend:
   • Sends the text to the Python ML service.
   • Extracts significant keywords from the text.
   • Combines results and returns them to the client.

---

Testing

Using curl

Send a POST request:

curl -X POST -H "Content-Type: application/json" -d '{"text": "I love this advanced AI app!"}' http://localhost:8080/predict

Using Postman

1. Create a new POST request.
2. Set the URL to http://localhost:8080/predict.
3. Add a JSON body with the text field.
4. Send the request and view the response.

---

Future Enhancements

1. Docker Integration:
   • Containerize both the Go and Python services for easier deployment.
2. Batch Processing:
   • Allow analysis of multiple text inputs in a single request.
3. Advanced NLP:
   • Use libraries like spaCy for sophisticated keyword extraction.
4. Multilingual Support:
   • Add models for other languages to expand the app's capabilities.

---

License

This project is licensed under the MIT License.

---

Contributions

Contributions are welcome! Feel free to open issues or submit pull requests to improve the application.