AI Takes on The Beatles

Harvard University researchers have announced a collaboration with Canda’s Dalhousie University to analyze Beatles songs - to better determine who wrote what.


Summary, from LinkedIn:

Paul McCartney and John Lennon of the Beatles wrote some of the most famous songs in history, yet for the songs where they are listed as co-authors, it's not clear who wrote what. With the help of algorithms and machine learning, a team of researchers from Harvard and Canada's Dalhousie University developed a system where they were able to correctly differentiate Lennon’s tracks from Sir Paul’s with 76% accuracy. They then applied this model to eight songs or fragments of songs whose authorship is a bit murky.

Mark Glickman, Senior Lecturer on Statistics at Harvard University, posted:

Our article, "(A) Data in the Life: Authorship Attribution in Lennon-McCartney Songs", was just published in the first issue of the HARVARD DATA SCIENCE REVIEW, the inaugural publication of @harvarddatascience published by the @mitpress. Combining features of a premier research journal, a leading educational publication, and a popular magazine, HDSR leverages digital technologies and data visualizations to facilitate author-reader interactions globally. Besides our article, the first issue features articles on topics ranging from machine learning models for predicting drug approvals to artificial intelligence.

Read the full piece here, and let us know what you think. The Independent has also covered this story.

Many remember Sir Paul’s latest visit to Cincinnati included a meeting with King Records alumni Otis Williams and Philip Paul - and there’s an image at Herzog of that encounter.