Come Together: Analyzing Popular Songs Through Statistical Embeddings
For musicologists and data scientists, it provides a novel method to statistically analyze non-standard musical data, though the application is limited to a small, specific corpus.
The paper uses logistic principal component analysis to create embeddings from global song features, enabling statistical analysis of popular music. Applied to Lennon-McCartney songs (1962-1966), it examines clustering by album, stylistic evolution, and convergence/divergence between the two songwriters.
Statistical modeling of popular music presents a unique challenge due to the complexity of song structures, which cannot be easily analyzed using conventional statistical tools. However, recent advances in data science have shown that converting non-standard data objects into real vector-valued embeddings enables meaningful statistical analysis. In this work, we demonstrate an approach based on logistic principal component analysis to construct embeddings from global song features, allowing for standard multivariate analysis. We apply this method to a corpus of Lennon and McCartney songs from 1962-1966, using embeddings derived from chords, melodic notes, chord and pitch transitions, and melodic contours. Our analysis explores how these song embeddings cluster by Beatles album, how songwriting styles evolved over time, and whether Lennon and McCartney's compositions exhibited convergence or divergence. This embedding-based approach offers a powerful framework for statistically examining musical structure and stylistic development in popular music.