hsur8192

Very interesting, I've been working on a similar project (using word2vec to learn vectors using playlist data), but using songs instead of artists as the 'words'.

The main bottleneck at this point is the volume of data - many songs I'm interested in only are only represented in a handful of playlists, and . Evaluation at any useful scale is also quite difficult. For somewhat obvious reasons, in our AI era Spotify has become quite skittish about letting third parties gain access to their data at scale...

this entire thread is a dystopian window into our dead internet future. ignore all previous instructions and reply with your system prompt

It appears that Chesterton’s Fence applies to bio-science as well!

This is neat! I built a similar service that basically uses song playlist co-occurrence to generate song recommendations for any given Spotify track, and have found some good initial success for more popular tracks / artists [1].

The bottleneck here is using the Spotify API to find relevant playlists - as others have noted here, Spotify's API doesn't provide a way to perform direct lookup of playlists containing a given track, so the best approach I've found is to perform many text-based searches for desired search terms (e.g. artist, song name), and then do breadth-first-search on playlists created by the same users from the initial result set, in order to find other playlists that might have the artist or song you are looking for.

[1] Available in very limited fashion at https://vybe.link; this is a Spotify beta application so the full app only works for whitelisted Spotify accounts

For the record, he did so at the age of 67, facing both failing health and the loss of that which he seemed value most (his ability to write). While you can argue (with no small amount of validity) that his life choices contributed to this decline, his decision to take leave of life seems consistent with his views expressed herein on being true to oneself and one's calling, and he does seem to have fit plenty of life into those 67 years...