From Long to Short: Hit Song Evolution

Chart-toppers peaked in duration during the 1990s after decades of growth, while the once-popular fade-out technique largely disappeared after 2010.

About the Data

The Billboard Hot 100 Number Ones Database represents a comprehensive collection of data about every song to reach number one on the Billboard Hot 100 between August 4, 1958 and January 11, 2025. This extensive dataset was meticulously compiled by Chris Dalla Riva over seven years as part of his research for the book Uncharted Territory: What Numbers Tell Us about the Biggest Hit Songs and Ourselves, and continues to power his music analytics newsletter Can’t Get Much Higher. The database contains detailed information across 87 variables for each chart-topper, including musical characteristics sourced from Spotify, genre classifications from both Dalla Riva’s team and Discogs, songwriter and producer credits from BMI/ASCAP databases, demographic information about artists, lyrical content analysis, and technical details like song structure, instrumentation, and recording characteristics. This rich dataset enables researchers to explore trends in popular music across nearly seven decades, from the evolution of song length and musical keys to changing patterns in artist demographics and lyrical themes, providing unprecedented insights into the cultural and musical landscape of American popular music.

Figure 1: This visualization maps the evolution of Billboard Hot 100 #1 hits from 1958 to 2025, with each horizontal line segment representing a chart-topping song. The x-axis shows song duration in seconds, centered at zero and extending symmetrically to show each song’s length. The y-axis displays the release year. Line segment width indicates weeks spent at #1, while colors distinguish between songs that fade out (orange) versus those with definitive endings (blue). Two curved trend lines trace the average duration boundaries over time, revealing how hit songs lengthened from the 1960s through 1990s before shortening again in recent decades, while the predominance of fade-outs has declined since 2010.

How I Made This Graphic

Loading required libraries

pacman::p_load(
  tidyverse,            # All things tidy
  
  scales,               # Nice Scales for ggplot2
  fontawesome,          # Icons display in ggplot2
  ggtext,               # Markdown text support for ggplot2
  showtext,             # Display fonts in ggplot2
  colorspace,           # Lighten and Darken colours

  patchwork,            # Composing Plots
  sf                    # Spatial Operations
)

# Using R
# Option 2: Read directly from GitHub

billboard <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/main/data/2025/2025-08-26/billboard.csv')

# topics <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/main/data/2025/2025-08-26/topics.csv')

Visualization Parameters

# Font for titles
font_add_google("Saira",
  family = "title_font"
) 

# Font for the caption
font_add_google("Saira Condensed",
  family = "body_font"
) 

# Font for plot text
font_add_google("Saira Extra Condensed",
  family = "caption_font"
) 

showtext_auto()

# A base Colour
bg_col <- "white"
seecolor::print_color(bg_col)

# Colour for highlighted text
text_hil <- "grey20"
seecolor::print_color(text_hil)

# Colour for the text
text_col <- "grey20"
seecolor::print_color(text_col)

line_col <- "grey30"

# Define Base Text Size
bts <- 80

# Caption stuff for the plot
sysfonts::font_add(
  family = "Font Awesome 6 Brands",
  regular = here::here("docs", "Font Awesome 6 Brands-Regular-400.otf")
)
github <- "&#xf09b"
github_username <- "aditya-dahiya"
xtwitter <- "&#xe61b"
xtwitter_username <- "@adityadahiyaias"
social_caption_1 <- glue::glue("<span style='font-family:\"Font Awesome 6 Brands\";'>{github};</span> <span style='color: {text_hil}'>{github_username}  </span>")
social_caption_2 <- glue::glue("<span style='font-family:\"Font Awesome 6 Brands\";'>{xtwitter};</span> <span style='color: {text_hil}'>{xtwitter_username}</span>")
plot_caption <- paste0(
  "**Data:**  Chris Dalla Riva", 
  " |  **Code:** ", 
  social_caption_1, 
  " |  **Graphics:** ", 
  social_caption_2
  )
rm(github, github_username, xtwitter, 
   xtwitter_username, social_caption_1, 
   social_caption_2)

# Add text to plot-------------------------------------------------
plot_title <- "Shorter Songs, Cleaner Endings"

plot_subtitle <- "Billboard #1 hits grew longer from 1960-1990s then shortened again, traced by curved trend lines showing duration boundaries. Fade-outs dominated until 2010 when definitive endings took over." |> 
  str_wrap(100)

str_view(plot_subtitle)

Exploratory Data Analysis and Wrangling

# billboard |> 
#   ggplot(
#     mapping = aes(
#       x = length_sec
#     )
#   ) +
#   geom_histogram(
#     fill = "white",
#     colour = "grey20",
#     bins = 100
#   )
# 
# billboard |> 
#   distinct(cdr_genre)
# 
# pacman::p_load(summarytools)
# billboard |> 
#   dfSummary() |> 
#   view()

plotdf <- billboard |> 
  mutate(
    length_x_min = 0 - (length_sec/2),
    length_x_max = 0 + (length_sec/2),
    colour_var = case_when(
      artist_male == 0 ~ "Female",
      artist_male == 1 ~ "Male",
      artist_male == 2 ~ "Both Male and Female",
      artist_male == 3 ~ "Both Male and Female"
    ),
    date = as_date(date)
  )

The Plot

g <- plotdf |> 
  ggplot() +
  geom_segment(
    mapping = aes(
      y = date,
      yend = date,
      x = length_x_min,
      xend = length_x_max,
      linewidth = weeks_at_number_one,
      colour = as_factor(fade_out)
    ),
    alpha = 0.5
  ) +
  geom_vline(
    xintercept = 0,
    linewidth = 3,
    alpha = 0.2,
    colour = "black"
  ) +
  geom_smooth(
    mapping = aes(x = length_x_min, y = date, group = 1),
    orientation = "y",
    formula = y ~ poly(x, 3),
    linewidth = 1.5,
    colour = alpha("black", 0.2),
    se = FALSE
  ) +
  geom_smooth(
    mapping = aes(x = length_x_max, y = date, group = 1),
    orientation = "y",
    linewidth = 1.5,
    formula = y ~ poly(x, 3),
    colour = alpha("black", 0.2),
    se = FALSE
  ) +
  scale_linewidth_continuous(
    range = c(0.1, 6),
    breaks = seq(3, 18, 3)
  ) +
  scale_x_continuous(
    limits = c(-200, 200),
    oob = scales::squish,
    breaks = seq(-200, 200, 40),
    labels = abs(seq(-200, 200, 40)),
    expand = expansion(0)
  ) +
  scale_y_date(
    expand = expansion(0),
    breaks = seq(as.Date("1960-01-01"), as.Date("2020-01-01"), by = "10 years"),
    date_labels = "%Y"
  ) +
  scale_colour_manual(
    values = paletteer::paletteer_d("nbapalettes::knicks")[1:2],
    labels = c("The Song does\nnot fade out", "The Song\nfades out")
  ) +
  guides(
    linewidth = guide_legend(
      nrow = 1
    ),
    colour = guide_legend(
      override.aes = list(
        size = 5, shape = 20,
        linewidth = 10
      )
    )
  ) +
  labs(
    title = plot_title,
    subtitle = plot_subtitle,
    y = "Year",
    x = "Duration of the song (in seconds)",
    caption = plot_caption,
    linewidth = "Total Weeks spent as No. 1",
    colour = "Does the song fade out?"
  ) +
  coord_cartesian(clip = "off") +
  theme_minimal(
    base_family = "body_font",
    base_size = bts
  ) +
  theme(
    
    legend.position = "bottom",
    legend.margin = margin(-15,0,0,0, "mm"),
    legend.box.margin = margin(-10,0,0,0, "mm"),
    legend.text = element_text(
      margin = margin(0,0,0,2, "mm")
    ),
    legend.title = element_text(
      margin = margin(0,0,3,0, "mm"),
      hjust = 0.5
    ),
    legend.title.position = "top",
    
    # Overall
    text = element_text(
      margin = margin(0,0,0,0, "mm"),
      colour = text_col,
      lineheight = 0.3
    ),
    
    # Axes
    axis.line.x = element_line(
      arrow = arrow(ends = "both", length = unit(5, "mm")),
      colour = line_col,
      linewidth = 0.5
    ),
    axis.line.y = element_line(
      arrow = arrow(length = unit(5, "mm")),
      colour = line_col,
      linewidth = 0.5
    ),
    axis.ticks = element_blank(),
    axis.ticks.length = unit(0, "mm"),
    panel.grid = element_blank(),
    panel.grid.major.x = element_line(
      linetype = 3,
      colour = "grey",
      linewidth = 0.3
    ),
    axis.text.x = element_text(
      margin = margin(4,2,2,2, "mm"),
      face = "bold",
      hjust = 0.5
    ),
    axis.text.y = element_text(
      margin = margin(2,2,2,2, "mm"),
      face = "bold"
    ),
    axis.title.y = element_text(
      margin = margin(0,0,0,0, "mm"),
      size = bts * 1.5
    ),
    axis.title.x = element_text(
      margin = margin(2,0,0,0, "mm"),
      size = bts * 1.5
    ),
    # Labels and Strip Text
    plot.title = element_text(
      margin = margin(5,0,5,0, "mm"),
      hjust = 0.5,
      vjust = 0.5,
      colour = text_hil,
      size = 3 * bts,
      family = "body_font",
      face = "bold"
      ),
    plot.subtitle = element_text(
      margin = margin(2,0,5,0, "mm"),
      vjust = 0.5,
      colour = text_hil,
      size =  bts,
      hjust = 0.5,
      family = "body_font",
      lineheight = 0.3
      ),
    plot.caption = element_textbox(
      margin = margin(5,0,2,0, "mm"),
      hjust = 0.5,
      halign = 0.5,
      colour = text_hil,
      size = bts * 0.8,
      family = "caption_font"
    ),
    plot.caption.position = "plot",
    plot.title.position = "plot",
    plot.margin = margin(5,5,5,5, "mm")
  )

ggsave(
  filename = here::here(
    "data_vizs",
    "tidy_billboard_hot_100.png"
  ),
  plot = g,
  width = 400,
  height = 500,
  units = "mm",
  bg = bg_col
)

Savings the thumbnail for the webpage

# Saving a thumbnail

library(magick)

# Saving a thumbnail for the webpage
image_read(here::here("data_vizs", 
                      "tidy_billboard_hot_100.png")) |> 
  image_resize(geometry = "x400") |> 
  image_write(
    here::here(
      "data_vizs", 
      "thumbnails", 
      "tidy_billboard_hot_100.png"
    )
  )

Session Info

pacman::p_load(
  tidyverse,            # All things tidy
  
  scales,               # Nice Scales for ggplot2
  fontawesome,          # Icons display in ggplot2
  ggtext,               # Markdown text support for ggplot2
  showtext,             # Display fonts in ggplot2
  colorspace,           # Lighten and Darken colours

  patchwork             # Composing Plots
)

sessioninfo::session_info()$packages |> 
  as_tibble() |> 
  dplyr::select(package, 
         version = loadedversion, 
         date, source) |> 
  dplyr::arrange(package) |> 
  janitor::clean_names(
    case = "title"
  ) |> 
  gt::gt() |> 
  gt::opt_interactive(
    use_search = TRUE
  ) |> 
  gtExtras::gt_theme_espn()

Table 1: R Packages and their versions used in the creation of this page and graphics

Links

• Billboard Hot 100
• Chris Dalla Riva
• Uncharted Territory: What Numbers Tell Us about the Biggest Hit Songs and Ourselves
• Can’t Get Much Higher
• Spotify
• Discogs
• BMI/ASCAP databases