> one other consideration is disliking can usually be inferred from other activity. Skipping a song after less then 20 seconds for example can train a model as well as incorporating an explicit dislike button.
This is nonsense. The fact that I skip a song does not mean I don't like it in general, it means I don't want to hear it right now. Music taste changes with mood and situation. If you treat a skip as "I don't ever want to hear this again" you will collect absolute garbage data, and if I know you are doing this, it will make your app unusable because I can't do normal everyday actions without ruining my recommendations.
It depends right. If you skip a song everytime its played in a sequence is a stronger indication of dislike compared to skip it once but listening to it a few times. The point is there is more to context and recommenders than a adding a dislike button and having a magically awesome recommender.
Have you read about illusion of control (search for elevator door button for one well known example)? If we take the idea that recommendations are really hard and dislike button doesn't help at face value, wouldn't it still improve the user experience to give them the illusion that they can directly affect the recommendations?
I'm not really convinced about recommendations being hard, though. Pandora could do them a long time ago, Netflix had good recommendations at one point but not since they dropped the star ratings and at some point Amazon wasn't that bad either.
This is nonsense. The fact that I skip a song does not mean I don't like it in general, it means I don't want to hear it right now. Music taste changes with mood and situation. If you treat a skip as "I don't ever want to hear this again" you will collect absolute garbage data, and if I know you are doing this, it will make your app unusable because I can't do normal everyday actions without ruining my recommendations.