The survey data is coming in.  So far I have over 80 responses with over 4,000 datapoints to use to evaluate recommendations.  This is very good data. Thanks to all who have submitted responses. Keep the data coming:  Take the survey
Comments:

I did this for Arcade Fire and one of the things that struck me as I went through it was the tension between making recommendations based on the sound of the music vs the reputation of the band. So for instance it was hard for me to see Arcade Fire fans being into My Chemical Romance not because of any sonic qualities, but I perceive the former is an arty hipster band for young twenty-somethings and the latter is a drama band for trendy yet ostrasized tweens. Coldplay and Radiohead? Too popular. Etc.

Just another data point to make it more complex.

Posted by Nancy Baym on September 10, 2007 at 09:27 AM EDT #

I also had the same feeling while answering the question. There's a lot of parameters that come into play when answering this list: more of a "sound like" approach (same production/same instruments), or the same "community" (canadian indie bands), or the totally egoistical "what I like" (even if that could mean Arcade Fire ~= Aphex Twin).

However, I feel that this fuzziness in interpretation is probably better (in the end) than to have an absolutely precise question. The good question would get a better answer faster, but would also be more limited in it's use. Given enough answers, I guess the statistical truth (the only truth that can be gained on music recommendations) will come out, and it will possibly transcend any precise question one could ask.

Posted by Marc-O on September 11, 2007 at 11:37 AM EDT #

Post a Comment:
Comments are closed for this entry.

This blog copyright 2010 by plamere