Cool!

A Data Scientist Analyzed the Lyrics to 222,623 Metal Songs and Came Up with This

Boing Boing reports on Iain (a guy who describes himself as an “ex-physicist currently working as a data scientist”) who has plenty of time on his hands. Culling through Dark Lyrics, a repository of metal lyrics, he analyzed 222,623 songs by 7,364 metal bands. Using the techniques of natural language processing, he was able to identify the words used most often in metal songs. Here are the top ten most metal words. (The number next to the word has to do with the measurement of its frequency in songs. Don’t ask me to explain that any further.)

  1. burn 3.81
  2. cries 3.63
  3. veins 3.59
  4. eternity 3.56
  5. breathe 3.54
  6. beast 3.54
  7. gonna 3.53
  8. demons 3.53
  9. ashes 3.51
  10. soul 3.40

What about the least metal words? Glad you asked.

  1. particularly -6.47
  2. indicated -6.32
  3. secretary -6.29
  4. committee -6.16
  5. university -6.09
  6. relatively -6.08
  7. noted -5.85
  8. approximately -5.75
  9. chairman -5.69
  10. employees -5.67

Alan Cross

is an internationally known broadcaster, interviewer, writer, consultant, blogger and speaker. In his 40+ years in the music business, Alan has interviewed the biggest names in rock, from David Bowie and U2 to Pearl Jam and the Foo Fighters. He’s also known as a musicologist and documentarian through programs like The Ongoing History of New Music.

Alan Cross has 39006 posts and counting. See all posts by Alan Cross

One thought on “A Data Scientist Analyzed the Lyrics to 222,623 Metal Songs and Came Up with This

  • i was thinking that this sort of analysis might be useful for looking where the “angry” political music might be- if it exists. It’s taking a quantitative look at the questions you were posing several weeks back.

    Sadly, I do not have the knowledge to do this myself.

    Reply

Let us know what you think!

This site uses Akismet to reduce spam. Learn how your comment data is processed.