Slashdot Mirror
Software Predicts Music Success
Frankenbuffer writes "The Globe and Mail today reports that MIT researchers have developed a computer program to analyze pop music and predict how people will react to it. The method, developed at MIT's Media Laboratory, analyzes the pitch, rhythm, and other characteristics of music. What makes the technology unusual is that it also takes into account social responses to hit music gathered from weblogs, chat rooms, music reviews, and other online discussions, and correlates this data to the music to guage the popularity of a particular sound. According to the researchers, the software has accurately predicted Billboard hits for the past several months."
This is not the first such program, and I suspect it shares the failing of its predecessors... It will not predict new trends, it will only follow existing ones. The more it is used to decide if an artist is going to be promoted, the less variety we will see in the music world. When new artists can no longer make it unless they are cookie-cutter copies of current acts (which has arguably already happened), the mainstream music scene will cease to evolve, and the really progressive, groundbreaking groups with a chance to become superstars and jumpstart new genres will be buried even farther under a pile of sameness.
On a personal level, I think we're going to head into an era where experimentation and unique sounds will be cherished. We've been listening to this sort of tin-pan alley redux for about 10-20 years now, and a lot of people sense discomfort with the existing pop music trends. Look at the 40s-70s and I think you'll see the same sort of musical revolution in the next 30 years.
We don't need software to predict how many posts will mention Britney Spears even though she faded away years ago. She's no longer an appropriate proxy for manufactured pop music. Pay attention people. It's 50 Cent's world, we just live in it.
Remember, this is for analysis of "pop" music. Kind of a contrast from what most indie artists are shooting for.
Trying to shape a song so it becomes successful has been tried many times before - with unsatisfying success. On a higher level it led to the categories of music we know today, like Blues, Trance, Metal, etc.. On a lower level we see follow-ups to first hits, that use the same kind of harmonies, rhythm and sounds. But there still are a lot of songs that become successful not because they sound the same like other songs but because they are innovative, think Kraftwerk or Nirvana.
Music trends are a system between unification and diversification. The more songs sound alike, the more people will appreciate songs that differ and vice versa. This system is very hard to predict. I am sure the music industry tries to predict it and synthesize hit records and I think this is why there are so few truely creative artists with a contract from a major record label.
On se Internetz nobody noes your German.
Quite the opposite, actually.
If it rates them high, it means it does a pretty good job of guessing at what kind of tripe the masses'll buy up, which is my understanding of what it's supposed to do