Frontiers in Artificial Intelligence
Accurately predicting hit songs using neurophysiology and machine learning
Sean H. Merritt
Kevin Gaffuri
Paul J. Zak- 1Center for Neuroeconomics Studies, Claremont Graduate University, Claremont, CA, United States
- 2Immersion Neuroscience, Henderson, NV, United States
Identifying hit songs is notoriously difficult. Traditionally, song elements have been measured from large databases to identify the lyrical aspects of hits. We took a different methodological approach, measuring neurophysiologic responses to a set of songs provided by a streaming music service that identified hits and flops.
Music is an effective way to influence people's emotional states (Fitch, 2006). Music and language likely co-evolved, with the first evidence of musical instruments appearing in Paleolithic bone flutes 40,000 years ago...
Examples include:
- Gregorian chants
- The sacred music of Bach
- The Tridentine Mass sung in Latin
- Navajo priest singers
- Buddhist & Daoist mantras
- Pygmy honey-gathering songs
- Country line dancing
- The Macarena
- Gangnam Style
- Boot camp recruit marching cadences
