Inspired by this Ted Talk by Colin Morris titled Pop Music is Stuck on Repeat I was interested in whether Taylor Swifts' songs have become more repetitive over time. In the Ted talk Morris talks through this essay where he outlines his strategy to quantify repetitiveness in songs using the Lempel-Ziv-Wilch (LZW) compression algorithm.
I've sourced all the the Taylor Swift lyrics from this Kaggle dataset and bootstrapped some of the exploratory data analysis using the this Kaggle kernel.
Taylor Swift has undergone some drasitic changes since her first album in 2006 and in this notebook we investigate three questions:
- Has Taylor's songs become shorter over time?
- Has Taylor's songs become happier over time?
- Has Taylor's songs become more repetitive over time?
A medium blog summarising my findings can be found here.
You can clone the repo by running
git clone https://github.com/louwjlabuschagne/tay-tay-text-theatre.git
You might not have textblob, worldcloud or nltk install, you can install these packages by running
pip install textblob
pip install wordcloud
pip install nltk