Tasks…
I picked up David Jenning’s “Net, Blogs and Rock’n’Roll”, and am working through it. Of most interest to me so far are Alan Lomax’s “cantometrics” work back in the 60s and MusicIP now (including MyDJ). I’m wondering how successful MusicIP has been… What’s it lacking and what do they do well?
Also been working on setting up LaTeX + GUI + citation handling software… argh! … and some revision control for this project. Right now I think I’ll go with BibDesk and TeXShop for writing with LaTeX, and subversion for RCS. Any advice welcome, as always.
Comment by Paul Lamere
Posted on January 31, 2008 at 6:48 am
My experience with MusicIP is mixed at best. First, it took about 15 days for MuiscIP to analyze my modest (5,000 track collection). Their playlists generated strictly based on content similarity were not of high quality. They almost always had an outlier (e.g. harpsichord in the middle of heavy metal).
It seems that the first round of commercial content-based recommenders are really struggling. Pandora is going social, MusicIP is struggling and SoundFlavor never really got off the ground. I think one reason is that social similarity is really hard to beat for popular music – and people listen to popular music – so the social systems just work a lot better for a large percentage of listening.