Roon 1.8 preview (2 of 5)

Context & meaning, powered by Valence

When you think of discovering new music, you may think of reading a great review, or finding that you love the opening act at a concert. You might imagine a conversation with a friend – maybe one who really knows their music history or stays on top of new releases – who happens to know what you like, too.

You probably don’t think of a network of servers analyzing the listening habits of zillions of users, using collaborative filtering to identify patterns in the data and find other content that you just might like. That’s the reality of algorithmic recommendation, though, which is why it often falls short of expectations.

Valence does more than compare you to other users. It uses Roon’s deep metadata as its foundation, providing context about music and connections between the people who compose, perform, and produce it. Next, it considers your listening history before filtering for the results that are most popular, but only among listeners who are experts in that genre.

This multidimensional approach is what gives Valence recommendations meaning. The very idea of “Top performers of works by Johannes Brahms” (or any of the examples in this post) would be impossible without a fundamental understanding of composers, genres, time periods, geography, compositions, form, instrumentation, performers, and collaborations.

Tomorrow, we’ll be sharing a preview of the new browsing tools available in Roon 1.8!