[All work](/work?type=work)

# Spotify Playlist Demographics

A playlist, its artists, and whatever their Wikipedia pages would say about them, turned into charts.

[Source code](https://github.com/Slaymish/Spotify-Demographics-Analyzer)

Independent development. Python, Spotify, Wikipedia and language-model extraction.

![A ring of wedges of different lengths around a hollow centre, one wedge filled red.](https://cdn.sanity.io/images/qnuj1c4o/production/ba8c38d532ed09ada207955a284c03b8bbfc6775-1600x900.png?w=1280\&q=80\&auto=format)

Spotify gives the artist names, Wikipedia gives the biographies, and GPT turns the free text into fields that can be plotted, with cached records so a second playlist doesn't pay for the same lookups.

Biographies are incomplete and a model can misread them, so the demographic fields here are estimates from sources. It's a polite way of saying don't trust them too far.

## State

The retrieval, extraction and plotting workflow, with its limits stated in the readme.

[All work](/work?type=work)