# Mood Classification Using Listening Data

arXiv: https://arxiv.org/abs/2010.11512 · HTML: https://mlsanity.com/paper/2010.11512/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Oct 2020.

## Built on by (most cited first, 6 of 6)

- [Supervised and Unsupervised Learning of Audio Representations for Music Understanding](https://mlsanity.com/paper/2210.03799/) (2022)
- [Low-Resource Music Genre Classification with Cross-Modal Neural Model Reprogramming](https://mlsanity.com/paper/2211.01317/) (2022)
- [Automatic Collection Creation and Recommendation](https://mlsanity.com/paper/2105.01004/) (2021)
- [Multi-task Learning with Metadata for Music Mood Classification](https://mlsanity.com/paper/2110.04765/) (2021)
- [The Contribution of Lyrics and Acoustics to Collaborative Understanding of Mood](https://mlsanity.com/paper/2207.05680/) (2022)
- [Exploiting Device and Audio Data to Tag Music with User-Aware Listening Contexts](https://mlsanity.com/paper/2211.07250/) (2022)

## Abstract (arXiv)

The mood of a song is a highly relevant feature for exploration and recommendation in large collections of music. These collections tend to require automatic methods for predicting such moods. In this work, we show that listening-based features outperform content-based ones when classifying moods: embeddings obtained through matrix factorization of listening data appear to be more informative of a track mood than embeddings based on its audio content. To demonstrate this, we compile a subset of the Million Song Dataset, totalling 67k tracks, with expert annotations of 188 different moods collected from AllMusic. Our results on this novel dataset not only expose the limitations of current audio-based models, but also aim to foster further reproducible research on this timely topic.