This story starts on April 20, 2018. That day, one of my favourite artists died: Avicii. Just a week before the sad news came in, I saw a documentary about his life: True Stories. The documentary ended on a positive note. This made the news of his death even harder for me. About a month after his death, I decided to see if I could analyse his songs in a way that would maybe give me a new insight into his life. I decided to use the lyrics as a starting point of my research. They included three of his releases: True, Stories and Avicii (ep).
I saved the lyrics of every song on the album into a text file and ended up with 32 files I could analyse. I analysed them using Google Cloud Natural Language API. The Google Cloud service allows you to use Google’s technical infrastructure in your own projects. Their Natural Language API is part of their ecosystem and allows a machine to ‘understand’ natural language (human speech). Using the Natural Language API, you can extract the sentiment from a piece of text. Assuming that Google is probably pretty good at that, I decided to apply that to the lyrics.
Turning Avicii’s Lyrics into data
Combining Avicii’s lyrics with the sentiment analysis allowed me to transform his discography into data points. Here’s an example of such a datapoint for the song ‘You Make me’:
title: 'you make me',
With all of his songs transformed into data points, the next step was to visualise the results. I did so using a scatter plot. On this plot, the horizontal axis represents the sentiment score ranging from -1.0 to +1.0. The vertical axis represents the magnitude (the strength of the expression).
Let’s have a look at the results for True:
As you can see, the songs are mostly positive. There is a big negative outlier in the top left corner that is both strong and negative. That song is ‘Liar Liar’.
Next up is his second release, Stories:
The sentiment of his second album seems to be way more positive. The negative songs are closer to the middle, and the positivity in the songs is way further to the right than the True songs were.
Third, Avici 01 (ep):
To me, this is the most balanced release of Avicii. It almost looks like an abstract butterfly, made of two negative songs, two neutral songs and two positive songs.
Looking for meaning
My original goal was to gain a better understanding of the sentiment in Avicii’s releases. To see if this would help me better understand his career. But after discussing the results with friends and colleagues, some doubts came up. People told me that (obviously) music is about more than just lyrics. It is about sounds. And lyrics can be interpreted in a multitude of ways.
I wasn’t sure if I was on the right track. I asked myself:
Am I capable of getting any true meaning out of this?
As I am no psychiatrist or (data) scientist, the answer was clear to me: no. I considered going back to redo the analysis to improve the outcome, but decided to take a different path.
I liked the overall shape of the plot: it’s an abstract visualisation of the discography of one of my favourite artists. Especially when I combine all of his songs in a single plot:
Taking my design out into the world
So I took a creative detour. First up: change the colours of the graph. I removed the colours based on sentiment and swapped them for colours based on the albums: blue for True, pink for Stories, and yellow for Avicii (ep). To make it printable, I had to clean up the plot by removing the graph elements. This resulted in the following plot:
After showing it to friends and colleagues, I came up with the idea to print in on an everyday object. All I had to do was prepare it for print and look for a website that would print my design on an everyday object. I chose to have the design printed on a t-shirt:
In the end, I’ve used my programming skills to generate a personal tribute to one of my favourite artists: Avicii. A tribute that I can wear everyday. I’m happy with that.
I have created a new type of visualisation after the release of Avicii’s posthumous album TIM. Read the story here.