Researchers at the University of California, Berkeley have developed a machine learning algorithm to analyze narrative storytelling in pop music lyrics. The study examined over 5,000 songs that appeared on the Billboard Hot 100 between 1960 and 2024, aiming to track changes in storytelling within popular music over the last six decades.
David Bamman, associate professor in the School of Information at UC Berkeley and first author of the study, explained the motivation behind the research: “We wanted to see if computational methods could measure the stories that are present in songs in order to help us understand how storytelling in music has changed on a larger scale over the past half of a century.”
Contrary to expectations that narrative storytelling peaked during the folk-driven era of artists like Joan Baez and Bob Dylan in the 1960s, researchers found an increase in narrativity since the 1990s. This trend is largely attributed to hip-hop’s rise in popularity. For example, Ice Cube’s “It Was a Good Day” ranked fifth for narrativity among all analyzed songs, just ahead of Taylor Swift’s “All Too Well,” which placed sixth. The lyrics of Ice Cube’s song detail daily life experiences, including seeking romance and coping with systemic challenges.
Tom McEnaney, corresponding author and associate professor at UC Berkeley as well as director of the Berkeley Center for New Media, commented on the value of computational analysis: “Many of us are excited about the computational modeling of cultural data because it grounds some of the claims that can be made from a smaller set of examples. When you have this larger set of data, you can get a picture of literary changes or developments that are clarifying and often go against the prevailing wisdom in that field.”
The team noted a shift in scholarly understanding regarding hip-hop’s lyrical complexity. “There was this assumption that poetry gets into popular music through hip-hop, and that hip-hop is the most lyric of genres,” McEnaney said. “If literary theory also tells us that lyric is non-narrative, then we wouldn’t expect to find hip-hop as the main driver of narrativity in popular music. But when you get to the 1990s, you just see the narrativity score shoot through the roof. This turns on its head the last 30 years of literary approaches to hip-hop.”
Bamman was inspired by Bruce Springsteen’s song “Thunder Road” to create tools for measuring narrative elements in lyrics. Reflecting on his experience hearing Springsteen’s work while abroad he said: “I finally got it, because the song is a story,” Bamman said. “It was really clear that Bruce Springsteen is a storyteller, and I could see how that would resonate with people.”
For more than ten years Bamman has been working on computational methods for analyzing cultural content such as literature and film. In previous research published last year he confirmed increasing diversity among actors in Hollywood films using facial recognition technology (With the help of AI, UC Berkeley researchers confirm Hollywood is getting more diverse).
To assess narrativity within pop songs, Bamman collaborated with undergraduate students Sabrina Baur, Mackenzie Hanh Cramer and Anna Ho. Together they reviewed lyrics from more than 1,000 popular songs using criteria such as presence of characters or agents, description of sequential events over time and world-building qualities.
The resulting dataset allowed them to train an algorithm capable of evaluating thousands more songs for their degree of storytelling.
Findings also indicated that narrative content may signal prestige within country music; Grammy-nominated country songs tended to contain higher levels of storytelling compared with other tracks from their respective albums.
McEnaney remarked on cross-genre similarities: “People often think of hip-hop as a primarily Black genre and country as a primarily white genre,” McEnaney said. “Beyoncé’s Cowboy Carter is only the most recent challenge to that assumption, and at a moment of absolute racial divisiveness in the country, it’s interesting to think about how those genres are the most popular genres and also have this shared interest in telling stories.”
