Quantifiable Data Assists Songwriters and Reveals The Mysteries Of Songwriting

How a group of engineers, developers, and musicians are unmasking the mysteries of songwriting using DATA.

Artificial intelligence and big data are transforming the way that we interact with and understand every aspect of our lives. Hooktheory, a Berkeley startup that builds interactive software and learning materials for songwriters and musicians, has created the world’s largest community-sourced database of popular song analyses. Hooktheory incorporates this data into its popular songwriting software Hookpad, to provide musical ideas informed by thousands of hit songs.

What makes a great song? 

Hooktheory believes that the growing “Theorytab” database is shedding light on a fundamental musical pursuit:  What exactly makes a great song?  In addition to its own work on the subject, Hooktheory has partnered with machine learning departments at Carnegie Mellon University and New York University to study this question.

(from left to right, co-founders Chris Anderson, Ryan Miyakawa, and Dave Carlton.)

Labor of love & musicians around the world

“The Hooktheory database owns more than [20,000] well-formatted tabs for popular music, which is a rare and precious data source for [many] tasks,” writes in an email Junyan Jiang, a researcher in computer music at Carnegie Mellon University, “the value of the Hooktheory database is unlimited.”

Over the past seven years, music enthusiasts from around the world have come to Hooktheory to build and maintain the world’s largest database of popular song analyses.  What started off as a labor of love by Hooktheory’s co-founders and friends, Dave Carlton, Chris Anderson, and Ryan Miyakawa, has grown into a massive community effort, with over 20,000 analyses of songs spanning all genres of music from Beyonce to Bon Jovi to The Beatles.  Each analysis called a “Theorytab” is similar in some ways to a guitar tab but powered by a simple yet powerful notation that stores the chord and melody information relative to the song’s key,  an important step that allows chords to be categorized by their musical function and that allows computers to easily parse through the data for patterns. It also goes a couple of steps further by allowing users to listen to a simple piano reduction of the analysis or the full recording powered by synchronization with the song’s YouTube music video.

“We’ve had an enormous response from our community of users who contribute to and maintain the Theorytab database every day,” says Chris, “We’re collaborating with researchers and developers in both the music and AI spaces, and believe that this data can reveal musical aspects that make us so drawn to our favorite songs, as well as provide a powerful tool for helping songwriters and musicians in their own musical pursuits.

Written By
More from Scope Weekly

SXSW 2019 Addresses Digital Distrust

SXSW 2019 unites tech, business, and entertainment to inspire innovation and creativity
Read More