Skip to content

lamfo-unb/MicrosoftEssexLDA

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

15 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

MicrosoftEssexLDA

This is a project executed between LAMFO (University of Brasilía) and UoE (University of Essex) in a collaboration fomented by Microsoft AI for Health for analysing misinformation regarding Covid-19 on News Outlets.

Pattern

Pattern for extracted data - Google Drive

Basic naming convention for columns: 'URL', 'Date', 'Source', 'Categories', 'Search Terms', 'Text', 'Author', 'Country'. There may have more optional columns (as index) but only this will be used as of now.

Naming convention for folders (regarding the project MicrosoftEssexScrapers): results/NAMEOFSOURCE

Naming convention for the file collected (please note there may be only one file per source): "articles.csv.zip" or "articles.zip" regardless of content (be it an article or not).

Other project links

Real time classification of text

Scrapers and data from news outlets

Heroku github project

Link to LDA training file

LAMFO project page

Project event with the Univesity of Essex

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published