Skip to content

A recommender system that uses crowdsourced data and Spotify public playlists to make recommendations to users

Notifications You must be signed in to change notification settings

emome/emome-processing

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

18 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

emome-processing

Code Climate

A recommender system that uses crowdsourced data and public Spotify playlists to make recommendations to users

What we've done

  • After pulling lyrics from the public Spotify playlists using Spotify API as well as Musixmatch API, NLPK tools and WNAffect are used to process and analyze the lyrics to extract the emotions of a song, where we currently used sadness, frustration, angryness, and anxiousness as the primary emotions. Representitive emotions are to be explored.
  • Given the four emotions of a song, we then use K-Means to classify different types of songs to make recommendations to the corresponding users.

About

A recommender system that uses crowdsourced data and Spotify public playlists to make recommendations to users

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages