A New Multilabel System for Automatic Music Emotion Recognition

TL;DR

This paper explores multilabel and multiclass machine learning methods for automatic music emotion recognition, focusing on the Geneva Emotional Music Scale 9 and analyzing algorithm performance on the Emotify dataset.

Contribution

It introduces a multilabel/multiclass framework for emotion recognition in music and compares various machine learning algorithms for this task.

Findings

Multilabel approach captures multiple simultaneous emotions.

Certain algorithms outperform others in emotion classification accuracy.

The Geneva Emotional Music Scale 9 effectively models music-induced emotions.

Abstract

Achieving advancements in automatic recognition of emotions that music can induce require considering multiplicity and simultaneity of emotions. Comparison of different machine learning algorithms performing multilabel and multiclass classification is the core of our work. The study analyzes the implementation of the Geneva Emotional Music Scale 9 in the Emotify music dataset and investigates its adoption from a machine-learning perspective. We approach the scenario of emotions expression/induction through music as a multilabel and multiclass problem, where multiple emotion labels can be adopted for the same music track by each annotator (multilabel), and each emotion can be identified or not in the music (multiclass). The aim is the automatic recognition of induced emotions through music.