DopeLearning: A Computational Approach to Rap Lyrics Generation

TL;DR

This paper introduces DopeLearning, a machine learning-based system for rap lyrics generation that predicts subsequent lines and combines existing lyrics to produce rhyming, meaningful rap verses, outperforming human rappers in rhyme density.

Contribution

It presents a novel prediction model using RankSVM and deep neural networks for rap lyric generation and demonstrates its effectiveness in creating rhyming, meaningful lyrics.

Findings

Prediction model achieves 17% accuracy in next-line prediction.

Generated lyrics have 21% higher rhyme density than top human rappers.

Online deployment as DeepBeat shows user preferences align with machine rankings.

Abstract

Writing rap lyrics requires both creativity to construct a meaningful, interesting story and lyrical skills to produce complex rhyme patterns, which form the cornerstone of good flow. We present a rap lyrics generation method that captures both of these aspects. First, we develop a prediction model to identify the next line of existing lyrics from a set of candidate next lines. This model is based on two machine-learning techniques: the RankSVM algorithm and a deep neural network model with a novel structure. Results show that the prediction model can identify the true next line among 299 randomly selected lines with an accuracy of 17%, i.e., over 50 times more likely than by random. Second, we employ the prediction model to combine lines from existing songs, producing lyrics with rhyme and a meaning. An evaluation of the produced lyrics shows that in terms of quantitative rhyme density, the method outperforms the best human rappers by 21%. The rap lyrics generator has been deployed as an online tool called DeepBeat, and the performance of the tool has been assessed by analyzing its usage logs. This analysis shows that machine-learned rankings correlate with user preferences.