http://musicmachinery.com/2009/05/25/artist-similarity-familiarity-and-hotness/ a blog about music technology by Paul Lamere Fri, 25 May 2012 19:11:43 +0000 hourly 1 http://wordpress.com/ http://musicmachinery.com/2009/05/25/artist-similarity-familiarity-and-hotness/#comment-2387 Thu, 23 Jul 2009 06:05:32 +0000 http://musicmachinery.com/?p=746#comment-2387 [...] Artist similarity, familiarity and hotness « Music Machinery [...]

]]> http://musicmachinery.com/2009/05/25/artist-similarity-familiarity-and-hotness/#comment-2093 Thu, 11 Jun 2009 04:35:53 +0000 http://musicmachinery.com/?p=746#comment-2093 [...] and yellow gauges in the picture above are familiarity and hotness ratings respectively. Check out this post by Paul Lamere for a detailed explanation of these [...]

]]> http://musicmachinery.com/2009/05/25/artist-similarity-familiarity-and-hotness/#comment-2003 Tue, 26 May 2009 11:17:34 +0000 http://musicmachinery.com/?p=746#comment-2003 lotb:
Best way to determine artist similarity? Not an easy question to answer. There are a number of ways – 1) self identification = where the artist says who they sound like. This is not always done, and is not consistent, also artists may position themselves closer to very popular artists in order to get some reflected popularity. 2) Expert identification – where a music expert creates a list of similar artists. This is what All Music Guide does. It can give you excellent results, but suffers from a scaling problem – it is hard to do this consistently for a million artists. (3) Collaborative filtering – people who listened to X also listened to Y – this generates very good similarities for popular and mid-tail artists. It has problems with long tail artist (aka the cold start problem), has problems with feedback loops (i.e. the rich get richer) and can be easily manipulated by hackers. (4) Web mining – reading news, reviews, blogs, playlists etc and applying statistical and natural language processing to the text to generate weighted descriptive terms for each artist and determining similarity based upon how these terms overlap between artists. This approach gives good similarity perhaps even deeper into the long tail than collaborative filtering, and is less subject to the feedback and hacking problems of CF. It is harder to get right, there are tricky web mining issues, for example, the band “the the” is difficult to deal with via this approach. (5) Content-based – perform signal processing and machine learning to the audio to build an audio based music similarity function. This approach is immune to the coldstart, hacking and feedback loops but is much harder to implement. Results are not always relevant. The best approach is a hybrid approach that will combine all of these approaches into a single similarity function.

]]> http://musicmachinery.com/2009/05/25/artist-similarity-familiarity-and-hotness/#comment-2001 Mon, 25 May 2009 20:13:33 +0000 http://musicmachinery.com/?p=746#comment-2001 Interesting. What do you think is the best method of determining artist similarity?

]]>