Sentiment Analysis on Product Review

This is the repository for the Sentiment Analysis on Product Reviews for classifying positive and negative reviews.

Built Using Machine Learning

Project Breakdown

Training Model

Backend support to get prediction for a review using API

Frontend support for users to interact with API

---

Training Machine Learning Model

Fetching Data

Cleaning Data

Fitting the model for highest accuracy

Saving the model

👇 Checkout the jupyter notebook of the trained model

---

Backend Server

The Backend server is written using Python Framework FastAPI and hosted on Heroku

Post request with product review will return a response about the type of rating

👇 Read More about the documentation of API

---

Frontend

The Frontend is written using Python Framework Streamlit and hosted on Streamlit hosting service

Single Review Analysis

Multiple Review Analyis(File upload with format as csv)

👇 Checkout the website

---

UI Design

---

🛠 Local Setup

1. Clone the repo
>> git clone repo_link

2. Change your current directory to the repo
>> cd directory_name

3. Activate virtual environment
>> $base> python -m venv venv
>> $base> .\venv\Scripts\activate

4. Run the backend server
>> (venv) $base> cd Backend
>> (venv) $base/Backend> pip install -r requirements.txt
>> (venv) $base/Backend> uvicorn main:app --reload

5. Run the frontend server(make sure to edit url for API calls to backend server url)
>> (venv) $base> cd Frontend
>> (venv) $base/Frontend> pip install -r requirements.txt
>> (venv) $base/Frontend> streamlit run main.py

Contributing

Pull requests are welcome.

For major changes, please open an issue first to discuss what you would like to change.

Show some ❤️ and ⭐ the repo to support the project

License

GPL-3.0 License

Star the Repo in case you liked it :)

© kehsihba19