This is the repository for our final project in computational social science 2022: Analysing Song Artists and Lyrics Through Genius.
The project was developed by:
Name | Student number |
---|---|
David Ari Ostenfeldt | s194237 |
Kristian Rhindal Møllman | s194246 |
Kristoffer Marboe | s194249 |
We make use of several APIs to collect data:
- billboard.py to get a list of songs from Billboards 'Hot-100' chart going all the way back to 1958.
- LyricsGenius to collect song titles, artists, release date and lyrics for the songs.
The data set used in the project can be downloaded here:
Data Set | Songs | Size (mb) |
---|---|---|
Billboard List | 29,128 | 1.6 |
Pre-cleaned | 29,128 | 92.5 |
Cleaned | 25,419 | 44.2 |
The file explainer-notebook.ipynb
contains all the code used to gather data and perform the network and text analyses.
The website is built on the HUGO framework and the TailwindCSS framework. The template used is a modified and expanded version of project-website-template by Pietro Rampazzo.