Suicidal Tendencies: The Automatic Classification of Suicidal and Non-Suicidal Lyricists Using NLP

Can natural language processing be used to predict the likelihood that a musician will commit or has committed suicide? In order to explore this idea, we built a corpus of songs that includes a development set, a training set, and a test set, all consisting of different lyricists. Various vocabulary and syntactic features were then calculated in order to create a suicide/nonsuicide song classifier. The features were input into the Weka machine learning suite and tested with an array of algorithms. We were able to achieve up to a 70.6% classification rate with the SimpleCart algorithm, a 12.8% increase over the majority-class baseline. Our findings suggest that syntactic and vocabulary features are useful indicators of the likelihood that a lyricist will commit or has committed suicide.