Skip to content
This repository has been archived by the owner on Jul 20, 2020. It is now read-only.

gartangh/Big-Data-Project

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

25 Commits
 
 
 
 
 
 
 
 

Repository files navigation

LET'S TWEET CORONA

Corona Deniers are everywhere. A few weeks ago, I was walking in a nearby department store. Here, I noticed a woman arguing with the shopkeeper. She stated several times corona does not even exist and that governments are just experimenting with new methods to keep us at home.

We call her a Corona Denier.

Who are they? And where do they live? All over the world, fake news is spreading regarding corona attacking corona believers, virologists and even China. If we can identify where these tweets come from, we can:

  1. Flag and remove the fake accounts.
  2. Make people faster aware of the problems with global disasters.
  3. Prevent situations like the one in the shop from happening again.

Project Status

This project is an easy-to-use Python API that addresses aforementioned prolems in the following way:

  • We were able to create and train a machine learning model with 98% accuracy that identifies whether or not a tweet stems from a corona denier or a corona believer.
  • We are able to visualize what continents and countries have more deniers.

Future Goals

Our next step would be to zoom in cities and neighbourhoods to identify hotspots around the globe.

Software requirements

  • Python 3.7.4
    • Tweepy 3.8.0
    • Scikit-learn 0.22.2
    • NLTK 3.4.5
    • pygal-maps-world 1.0.2
    • pycountry_convert 0.7.2
    • geopy 1.21.0

About

A Python API to distinguish Corona believers from deniers with the use of Machine Learning based Natural Language Processing.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages