At some point or another, every dance music fanatic has attempted to locate their crew at the function by scanning the crowd for their friends’ quirky dance moves. Now that method can be scientifically quantified.
It would seem our dance moves are as unique to us as our finger prints, according to an intriguing new study conducted at the Centre for Interdisciplinary Music Research at the University of Jyväskylä. Finnish researchers have found that a human’s dancing style is almost always the same regardless of what style of music they are dancing to.
It seems as though a person’s dance movements are a kind of fingerprint.” – Pasi Saari, Ph.D.
Using machine learning and motion capture technologies, computers are now able to identify people based on their dance moves. Pasi Saari, data analyst and co-author of the study, recorded and analyzed the movements of 73 people as they danced to eight different genres: blues, country, EDM, jazz, metal, pop, reggae and hip hop.
Researchers then used computer algorithms to correctly identify the participants’ dance moves 94 percent of the time. However, some dance styles were harder for the computer to identify than others. The technology had a difficult time deciphering people who were dancing to metal, according to one of the study’s researchers.
“There is a strong cultural association between metal and certain types of movement, like headbanging,” says Emily Carlson. ” It’s probable that metal caused more dancers to move in similar ways, making it harder to tell them apart.”
Of course, all good research raises more questions than answers. Researchers are hoping to go back in and study whether people’s dance moves stay the same over the course of our lifespans, whether cultural differences can be detected from people’s dance moves, and how well humans can detect others’ dance movements as compared to computers.
For those wondering whether the study raises ethical concerns, especially in light of the recent facial recognition software controversy at events, fret not. Researchers say they are “less interested in applications like surveillance” than a general curiosity “about human musicality.”
This research study was published in The Journal of New Music Research. View the full manuscript here.