This repository contains some analysis of the nCovMemory project, which was a database of articles linked to the coronavirus epidemy in China hosted on GitHub as well.
The nCovMemory repo has since been deleted by its authors in fear of reprisal by the chinese authorities. However, many forks of the project still exist online and a version of the repo is still available on the Wayback Machine
In this repo, both the code to generate the analysis results' and the results are presented. I created a website to present the results only: https://alqua.github.io/website-nCovMemory-analysis/
The analysis complement the master thesis I wrote, in french, on the subject. The thesis is not available on this website but if you are interested, you can contact me.
The repo is divided into two main folder , DRAFT and ANALYSIS. I did three kind of analysis:
- Data graphs on articles
- LDA theme analysis
- Maps
contains the first analysis I made on an earlier version of the nCovMemory database. I won't be commenting the files in this folder as much as the other but it can be interesting to have a look. The process I went through with those analysis lead to choices made with the actual analysis presented.
Contains the analysis I actually used and the code to generate them. Each folder contains another README describing the content of the folder and some brief explainations.
In case you are interested to re-use the code, I did reorganise files and folders to present them here. That means that paths are likely broken. Just pay attention to that :)
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.