This Study Shows How All The Music Videos On YouTube Connect To One Another

Music videos get many millions of hits each day on YouTube, but how do all those views fit together? That’s the question a team of Italian researchers sought to answer in a recent paper titled “Follow the algorithm: An exploratory investigation of music on YouTube,” which studies the patterns that link together digital music videos

The research team, led by Massimo Airoldi, tracked user behavior by following a path of “related videos” generated by YouTube’s algorithm. “This article presents an exploratory study of the network of associations among 22,141 YouTube music videos,” reads the study’s abstract. “As YouTube’s recommendations are predominantly based on users’ aggregated practices of sequential viewing, this study aims to inductively reconstruct the resulting associations between the musical content in order to investigate their underlying meanings.”

To put that in layman’s terms, the study’s goal was to create “clusters” of related music videos that are often watched by the same users. Ultimately, 50 of these clusters emerged: Some of them, such as “pop hits,” “rock 90s,” and “country,” are closely tied to existing musical genres. At the same time, a second group of clusters caters to viewers who look to establish a specific mood through their musical choices. Those categories include “relaxing background music,” “epic music/soundtrack,” and “music for babies.”

When linked together in a single matrix, the clusters fall into two rough halves, with genre-based clusters on one side and mood-based clusters on the other. Pop music, for example, is much closer to rock and country than it is to music for babies. The most significant link between these two supergroups — that is, the cluster chosen both for mood and genre purposes, is the “Piano/Violin Cover” category occupied by artists like Lindsey Stirling.

For additional analysis of the study, head over to New York Magazine.