Musical Attribute Analysis

The purpose of this project is to analyze the different attributes of songs and discover how they have changed over the years. In our research, we decided to plot our data using a multi-line chart to discover trends, plot a scatter chart to see relationships between attributes, and use a radar chart giving us the ability to compare artists of different eras.

We have also used Machine Learning to expand on the project. Taking all of the tracks in our dataset, we use K-Means Clustering to cluster tracks together to other similar tracks, based on the track's scaled attributes, with the optimal cluster number of 10.

A confidence measure of how acoustic a song is.
Range: 0.0 to 1.0

How suitable for dancing using tempo, rhythem stability, beat strength, and regularity.
Range: 0.0 to 1.0

A measure of intesity and activity using tempo, loudness, and noisiness.
Range: 0.0 to 1.0

How confident that a song has no vocals.
Range: 0.0 to 1.0

How confident that a song was performed in front of an audience.
Range: 0.0 to 1.0

Negative values are how much restriction is placed on a given system. The closer it is to 0, the louder it is.
Range: -∞ to 0

How much a song/track consists of entirely spoken words.
Range: 0.0 to 1.0

The speed or pace of a given track. Given in Beats per minute.
Range: 0.0 to ∞

How much positive emotion a song has.
Range: 0.0 to 1.0

This is a student project; we are not collecting any data. Spotify widgets do collect user data. See spotify terms.