https://github.com/eczy/live-sentiment-analysis

https://github.com/eczy/live-sentiment-analysis

Last synced: 11 days ago
JSON representation

• Host: GitHub
• URL: https://github.com/eczy/live-sentiment-analysis
• Owner: eczy
• Created: 2019-12-17T23:13:13.000Z (almost 5 years ago)
• Default Branch: master
• Last Pushed: 2024-10-22T03:32:26.000Z (16 days ago)
• Last Synced: 2024-10-23T05:26:31.520Z (15 days ago)
• Language: JavaScript
• Size: 746 KB
• Stars: 1
• Watchers: 2
• Forks: 0
• Open Issues: 1
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Live Sentiment Analysis

This is a toy web app that performs sentiment analysis on

textual user input as it is being written. Currently, this is only

designed to run in a dev environment, but with a few minor modifications

it can be deployed with any cloud service provider.

For sake of simplicity, speed, and lack of having a huge dataset for training,

this application uses a pre-trained rule based VADER model

([paper](https://www.researchgate.net/publication/275828927_VADER_A_Parsimonious_Rule-based_Model_for_Sentiment_Analysis_of_Social_Media_Text))

built into NLTK. There is an npm package for VADER, but the application was

built with a backend so that more complex/computationally expensive models

can be used.

## How to run

1. Clone this repo

2. Navigate to `/api`

3. Create a new virtual enivironment with the dependencies in `/api/requirements.txt`

4. Specify `app.py` as the Flask app to run: `export FLASK_APP=app.py`

5. Run the Flask application: `flask run`

6. In a new terminal (or the same if you ran Flask in the background), navigate to `/ui`

7. Install the React frontend and run the dev server: `npm i; npm start`

8. Go to `localhost:3000` and experiment!