Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Lyrically Speaking: Exploring the Link Between Lyrical Emotions, Themes and Depression Risk

Pavani Chowdary, Bhavyajeet Singh, Rajat Agarwal, Vinoo Alluri

TL;DR

This study addresses whether lyric content in online listening histories reflects depression risk. It analyzes Last.fm data from 541 users, mapping lyrics to a Valence-Arousal space with an XLNet-based classifier and quantifying semantic themes via DICTION, then testing differences between At-Risk and No-Risk groups using Mann-Whitney U tests. Results show At-Risk listeners favor songs with low valence/low arousal lyrics and higher frequencies of Denial, Self-reference, and Blame themes, suggesting potential for digital-footprint-based depression risk assessment and targeted recommendations. While informative, the work notes limitations such as lyric-only focus and language constraints, outlining multi-modal future work to enhance risk prediction and intervention strategies.

Abstract

Lyrics play a crucial role in affecting and reinforcing emotional states by providing meaning and emotional connotations that interact with the acoustic properties of the music. Specific lyrical themes and emotions may intensify existing negative states in listeners and may lead to undesirable outcomes, especially in listeners with mood disorders such as depression. Hence, it is important for such individuals to be mindful of their listening strategies. In this study, we examine online music consumption of individuals at risk of depression in light of lyrical themes and emotions. Lyrics obtained from the listening histories of 541 Last.fm users, divided into At-Risk and No-Risk based on their mental well-being scores, were analyzed using natural language processing techniques. Statistical analyses of the results revealed that individuals at risk for depression prefer songs with lyrics associated with low valence and low arousal. Additionally, lyrics associated with themes of denial, self-reference, and ambivalence were preferred. In contrast, themes such as liberation, familiarity, and activity are not as favored. This study opens up the possibility of an approach to assessing depression risk from the digital footprint of individuals and potentially developing personalized recommendation systems.

Lyrically Speaking: Exploring the Link Between Lyrical Emotions, Themes and Depression Risk

TL;DR

This study addresses whether lyric content in online listening histories reflects depression risk. It analyzes Last.fm data from 541 users, mapping lyrics to a Valence-Arousal space with an XLNet-based classifier and quantifying semantic themes via DICTION, then testing differences between At-Risk and No-Risk groups using Mann-Whitney U tests. Results show At-Risk listeners favor songs with low valence/low arousal lyrics and higher frequencies of Denial, Self-reference, and Blame themes, suggesting potential for digital-footprint-based depression risk assessment and targeted recommendations. While informative, the work notes limitations such as lyric-only focus and language constraints, outlining multi-modal future work to enhance risk prediction and intervention strategies.

Abstract

Lyrics play a crucial role in affecting and reinforcing emotional states by providing meaning and emotional connotations that interact with the acoustic properties of the music. Specific lyrical themes and emotions may intensify existing negative states in listeners and may lead to undesirable outcomes, especially in listeners with mood disorders such as depression. Hence, it is important for such individuals to be mindful of their listening strategies. In this study, we examine online music consumption of individuals at risk of depression in light of lyrical themes and emotions. Lyrics obtained from the listening histories of 541 Last.fm users, divided into At-Risk and No-Risk based on their mental well-being scores, were analyzed using natural language processing techniques. Statistical analyses of the results revealed that individuals at risk for depression prefer songs with lyrics associated with low valence and low arousal. Additionally, lyrics associated with themes of denial, self-reference, and ambivalence were preferred. In contrast, themes such as liberation, familiarity, and activity are not as favored. This study opens up the possibility of an approach to assessing depression risk from the digital footprint of individuals and potentially developing personalized recommendation systems.
Paper Structure (16 sections, 2 equations, 4 figures, 1 table)

This paper contains 16 sections, 2 equations, 4 figures, 1 table.

Table of Contents

  1. Introduction
  2. Background and Related Work
  3. Methodology
  4. Dataset
  5. Measure of Depression Risk
  6. Listening History and Lyrics
  7. Lyrics Processing
  8. Lyrics-Emotion Mapping
  9. Lyrics-Semantic Themes Mapping
  10. Statistical Testing
  11. Statistical Testing and Results
  12. Lyrical Emotion-Based Results
  13. Lyrical Theme-based Results
  14. Discussion
  15. Limitations
  16. ...and 1 more sections

Figures (4)

  • Figure 1: Methodology
  • Figure 2: Two-dimensional Valence-Arousal space
  • Figure 3: Violin plots of mean QPS per quadrant for At-Risk and No-Risk groups
  • Figure :