It is not just teenage girls who like to listen to sad songs once in awhile. Sometimes it is that certain emotional quality that comes across in songs that fits the mood you are in or feeds the need for emotion in your life at a particular time. Similar to the thumping, dance-inspiring music that keeps me cleaning the house despite my desire to quit, particular tunes, rhythms and words can define your mood. This very interesting information came to us from Variety in their article, “Sad Songs, Artificial Intelligence and Gracenote’s Quest to Unlock the World’s Music.”
Music data specialists at Gracenote have long been classifying the world’s music by moods and emotions. They have taught computers to detect emotions, using machine listening and artificial intelligence to determine whether each and every one of the 100 million individual song records in its database is dreamy, sultry, or just plain sad.
Using machine learning to classify music by mood is not without its challenges. Teaching computers to identify emotions in music is similar to therapy. The first step is to name your feelings. Gracenote’s music team initially developed a taxonomy of more than 100 vibes and moods, and has since expanded that list to more than 400 such emotional qualities.
Classifying all of the world’s music is an endless task as music is constantly being created. However, teaching computers to detect a certain type of song based on emotions can actually help humans to have a better and more fulfilling music experience.
Melody K. Smith
Sponsored by Data Harmony, a unit of Access Innovations, the world leader in indexing and making content findable.
