My project work for the course CS-C4100 Digital Health and Human Behavior!
This work uses the dataset Tweets about Covid-19 all over the world dataset oublished by Komal Khetlani with can be accessed through Kaggle.
The dataset including translations can be found here: Google Drive. If the link is not working feel free to contact me via [email protected]
The notebooks called pre-processing found in the folder pre-preprocessing are the different workes used for the translation progress. The cells inside carry documentation.
The exploration notebook is used to produced all plots and is internally structured.
I used Python 3.8 and the libraries are all clearly marked in the first cell of each notebook
The file report.pdf
contains my findings.