Personalized musically induced emotions of not-so-popular Colombian music

TL;DR

This study explores how personalized music emotion recognition systems can be biased by political context, analyzing Colombian songs with charged lyrics to predict emotions and potential manipulation risks.

Contribution

It introduces a novel approach to biasing MER systems using politically charged music and demonstrates personalized emotion prediction for users with diverse political views.

Findings

Personalized models can predict induced emotions in politically charged music.

Emotion judgments can be used to identify potentially manipulative content.

Highlights ethical concerns in emotion recognition technology.

Abstract

This work presents an initial proof of concept of how Music Emotion Recognition (MER) systems could be intentionally biased with respect to annotations of musically induced emotions in a political context. In specific, we analyze traditional Colombian music containing politically charged lyrics of two types: (1) vallenatos and social songs from the "left-wing" guerrilla Fuerzas Armadas Revolucionarias de Colombia (FARC) and (2) corridos from the "right-wing" paramilitaries Autodefensas Unidas de Colombia (AUC). We train personalized machine learning models to predict induced emotions for three users with diverse political views - we aim at identifying the songs that may induce negative emotions for a particular user, such as anger and fear. To this extent, a user's emotion judgements could be interpreted as problematizing data - subjective emotional judgments could in turn be used to influence the user in a human-centered machine learning environment. In short, highly desired "emotion regulation" applications could potentially deviate to "emotion manipulation" - the recent discredit of emotion recognition technologies might transcend ethical issues of diversity and inclusion.