Reproduce “Predicting the top and bottom ranks of billboard songs using Machine Learning” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Vivek Datla, Abhinav Vishnu
Researchers from Pacific Northwest National Laboratory developed a computational approach to predict song popularity on Billboard charts using only machine learning analysis of lyrical content. Their Support Vector Machine model achieved 76% precision and recall, indicating that linguistic patterns in lyrics contain information relevant to commercial success.
Key insights
- Linguistic analysis of song lyrics can provide predictive power for a song's commercial success on Billboard charts, even without audio features.
- A multi-dimensional feature engineering framework capturing structural, syntactic, semantic, and psycholinguistic aspects of lyrics is effective for this prediction task.
- Support Vector Machines, particularly with an RBF kernel, are well-suited for classifying song popularity based on high-dimensional lyrical features.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.