These criteria aren’t easy to meet, and the result is lots of people like me who never listen to non-talk radio. But recently I’ve become obsessed with a new kind of (internet) radio station, one that’s converted me back from my CDs to the radio. It’s called Pandora, and its successes reveal interesting lessons about aggregating museum content.
Pandora uses collaborative filtering to create a real-time radio station for you based on your preferences. You enter a seed artist or song (or several) and Pandora starts playing music that it interprets as related in some way to your selections. The extraordinary thing about Pandora is the complexity of its filtering. It doesn’t just group artists together and play music by similar musicians. Instead, it uses hundreds of tags, signifiers assigned to each song by a team of musicians, to find correlated songs that may be of interest. Pandora is a product of the Music Genome Project, in which musicians define the individual “genes” of a song via signifiers and use those to generate song “vectors” that can then be compared to create highly specific and complex musical narratives.
For example, I created a radio station today based on just one song: Diamonds on the Soles of Her Shoes by Paul Simon. That radio station then played:
- She’s a Yellow Reflector by Justin Roberts
- If Only the Moon Were Up by Field Music
- She’s Going by The English Beat
- You’re The One by Paul Simon
- Withered Hope by They Might Be Giants
- Big Dipper by Elton John
- Wait Until Tomorrow by New York Rock and Roll Ensemble
- The Tide is High by Blondie
There are over 400 different tags used to relate songs in the Music Genome Project, ranging from “brisk swing feel” to “lyrics that tell a story” to “sparse tenor sax solo.” From a single seed song, Pandora will generate a whole channel of music, and will shift and refine that channel based on your thumbs up/down rating of each song played. In this way, Pandora makes inferences about what you might like and introduces you to new music.
And it’s the introduction to new music that makes Pandora uniquely interesting to me as a museum person. When we talk about allowing visitors to curate their own museum experiences by voting for exhibits or aggregating custom tours, the fear among curators is that such projects will denigrate the collection and turn the museum visit into a kind of popularity contest. In short, we fear that visitors, if given the tools to create their own narratives, won’t want or use the ones we provide.
Pandora is a model for an alternative. Rather than user-based collaborative filtering, in which visitors receive recommendations based on what other “people like you” enjoyed, Pandora is an example of item-based collaborative filtering, in which visitors receive recommendations based on the similarity of previously selected items (seed songs) to potential members of the collection.
Pandora and the Music Genome Project is controlled by experts, musicians who, like curators, are uniquely skilled at identifying and tagging songs to create musical genes that represent the full spectrum of musical expression. And their expertise makes for a better experience for me as a user/visitor. As an amateur listener, I could not tell you the particular elements of “Diamonds on the Soles of Her Shoes” that appeal to me. Listening and reacting to the Pandora-generated songs allowed me to understand the nuance of what I like and don’t like. Turns out that I enjoy songs with “extensive vamping.” Could I have articulated that at the start? No. Not only does Pandora introduce me to new music, it expands my vocabulary for discussing music. I learned something! From experts!
Users of Pandora are protective of the Music Genome Project experts. There have been interesting discussions on the Pandora blog about the slow inclusion of user-based filtering, and listeners' related fear that it will taint the waters of the high-quality item-based process. The Music Genome Project involves visitors' submissions in a limited way. The core value is in the professional categorization of the songs.
Which means that curators still have a powerful role to play in the future of museums. Imagine if an art museum worked this way, if curators tagged every piece with tags representing everything from “misogynistic undertones” to “Picasso blue period” to “asymmetrical” and generated a tour for you real-time on a handheld device. You could have a personalized trip through the museum, enjoying an experience that is both highly responsive to your preferences and one which deepens your understanding and ability to articulate why you like what you like. In some cases, people might be surprised to learn that they prefer artists whose subject matter comes from childhood memories, or those who work in a specific medium. While the museum can’t be physically rearranged for each visitor, the content can be remixed conceptually to present a progressively engrossing, educational experience.
Personalization doesn’t just give you what you want. It exposes you to new things, and it gives you a vocabulary for articulating and refining why you like what you like. Pandora’s collaborative filtering process contextualizes data from a very personal starting point. You get the analysis and the narrative, but you get the slice that will resonate most with you. The world is opened a little wider and hopefully, you keep listening.