I work in this industry and actually we’ve found from online experimentation customers generally don’t want to tell you they dislike something. The expectation is customers get what they like (relevant) and sometimes they want to express stronger affinity for specific things. The converse hasn’t shown to be true. Generally customers don’t have a clear picture of how their explicit signals impact recommendations. Thou…
Let me be one of those. I want to be able to control the algorithm in all of its parameters, but even the ability to control the values for new/familiar and how far to stray from the current genre would be very welcome.