An open API service indexing awesome lists of open source software.

https://github.com/k4u5h4l/sentinalyzer

A web app which detects the sentiment of a movie review, whether it is positive or negative.
https://github.com/k4u5h4l/sentinalyzer

django javascript jupyter-notebook keras-tensorflow neural-networks python react sentiment-analysis tensorflow tensorflow2

Last synced: 3 months ago
JSON representation

A web app which detects the sentiment of a movie review, whether it is positive or negative.

Awesome Lists containing this project

README

          

Sentinalyzer


:smile: A web app which detects the sentiment of a movie review, whether it is positive or negative. :unamused:




k4u5h4L GitHub badge


Sentinalyzer logo


## Technologies used:

- React (create-react-app) for the front end.

- Python-Django for the backend server side.

- Tensorflow 2.3.0 with the Keras syntax for the model training and predictions.

## To run:

- Clone and cd into the repo.

```
git clone https://github.com/k4u5h4L/Sentinalyzer.git && cd Sentinalyzer
```

- Cd into the client and install the required dependencies

```
cd client && npm install
```

- In the `server/form/views.py` file, change the file path of the model and pickle file.

- Install the dependencies from the `requirements.txt` file

```
pip install -r requirements.txt
```

- Run the Django server.

```
python manage.py runserver
```

- In another terminal, run the front end React client.

```
npm start
```

- Now visit the location [localhost:3000](http://localhost:3000) to visit the site.

## Note:

- This project is made as a hobby and is NOT a commercial application.

- Any contribution is welcome. You can fork and submit a pull request.

- The dataset is got from [kaggle](https://kaggle.com) from [this page](https://www.kaggle.com/lakshmi25npathi/imdb-dataset-of-50k-movie-reviews) by [lakshmi25npathi](https://www.kaggle.com/lakshmi25npathi).
Please download the dataset and unzip the csv file in this file path `data/imdb_movie_reviews/IMDB_Dataset.csv` to train the model yourself.