2021/03/30 by Megan Mansfield, Mansfield, Megan, Darryl Seligman +2
Arts and Humanities · Computer Science · Neuroscience · #Earth and Planetary Astrophysics (astro-ph.EP) #FOS: Physical sciences #Music History and Culture #Music Technology and Sound Studies #Music and Audio Processing #Neuroscience and Music Perception #Popular Physics (physics.pop-ph)
paper · pdf · doi:10.48550/arxiv.2103.16737
openalex publication_date 2021/03/30 · openalex created_date 2022/07/25 · openalex updated_date 2026/07/28
As a modern musician and cultural icon, Taylor Swift has earned worldwide\nacclaim via pieces which predominantly draw upon the complex dynamics of\npersonal and interpersonal experiences. Here we show, for the first time, how\nSwift's lyrical and melodic structure have evolved in their representation of\nemotions over a timescale of \τ\∼14 yr. Previous progress on this topic\nhas been challenging based on the sheer volume of the relevant discography, and\nthat uniquely identifying a song that optimally describes a hypothetical\nemotional state represents a multi-dimensional and complex task. To quantify\nthe emotional state of a song, we separate the criteria into the level of\noptimism (H) and the strength of commitment to a relationship (R), based on\nlyrics and chordal tones. We apply these criteria to a set of 149 pieces\nspanning almost the entire repertoire. We find an overall trend toward positive\nemotions in stronger relationships, with a best-fit linear relationship of\nR=0.642+0.086-0.053H-1.74+0.39-0.29. We find no significant\ntrends in mean happiness (H) within individual albums over time. The mean\nrelationship score (R) shows trends which we speculate may be due to age and\nthe global pandemic. We provide tentative indications that partners with blue\neyes and/or bad reputations may lead to overall less positive emotions, while\nthose with green or indigo-colored eyes may produce more positive emotions and\nstronger relationships. However, we stress that these trends are based on small\nsample sizes, and more data are necessary to validate them. Finally, we present\nthe taylorswift python package which can be used to optimize song selection\naccording to a specific mood.\n