Sketch for an idea for a hack day at Last.fm. The theme is “user profiles”. I’m working on a project with Mark Levy, who leads the Music Information Retrieval team, to chart the mood of a user’s listening over time using new audio analysis tagging. We will be testing it on the team first!
I call it MOODmongr
In general, the moods were pretty even across the year’s listening of my test group; my team mates. This was largely due to the fact that we all have varied music tastes and use radio steams and playlists for variety. However there were a few spikes and points of interest:
The interface consisted of two input boxes, one to put in what you wanted to play using a mix of tags, artists, and user profiles, and one that would exclude things you don’t like (e.g. Coldplay, Adele and “industrial house” in my case!). To get a flavour of the music the station would play, we added a quilt of artists and tags, that you could fine tune by deleting tiles from the quilt. Once you were happy, you could then play, save or share the station.
We called it “Radiomongr”. Unfortunately the prototype isn’t available for public viewing, but hopefully it can be used as a model for a releasable product at some point.