Quantifying Cultural Change: Gender Bias in Music

• Published in: Journal of experimental psychology. General 2023-09, Vol.152 (9), p.2591-2602
• Main Authors: Boghrati, Reihane, Berger, Jonah
• Format: Article
• Language: English
• Subjects: Bias; Culture; Culture Change; Desire; Female; Gender; Gender Bias; Human; Male; Misanthropy; Music; Natural language processing; Stereotyped Attitudes; Stereotypes
• ISSN: 0096-3445; 1939-2222
• DOI: 10.1037/xge0001412

Cultural items (e.g., songs, books, and movies) have an important impact in creating and reinforcing stereotypes. But the actual nature of such items is often less transparent. Take songs, for example. Are lyrics biased against women, and how have any such biases changed over time? Natural language processing of a quarter of a million songs quantifies gender bias in music over the last 50 years. Women are less likely to be associated with desirable traits (i.e., competence), and while this bias has decreased, it persists. Ancillary analyses further suggest that song lyrics may contribute to shifts in collective attitudes and stereotypes toward women, and that lyrical shifts are driven by male artists (as female artists were less biased to begin with). Overall, these results shed light on cultural evolution, subtle measures of bias and discrimination, and how natural language processing and machine learning can provide deeper insight into stereotypes, cultural change, and a range of psychological questions more generally. Public Significance StatementGender bias is pervasive. One reason biases may be so persistent is that they are continually reinforced through cultural items like songs. We use natural language processing and analyze over 50 years of lyrics to quantify gender bias in music over time. Lyrics tend to associate desirable traits (i.e., competence) with men, and while this bias has decreased over time, it persists. The temporal change is mainly driven by male artists, as female artists were less biased to begin with. Overall, these results shed light on cultural evolution, subtle measures of bias and discrimination, and how natural language processing and machine learning can provide deeper insight into stereotypes, cultural change, and a range of psychological questions more generally.