6,110 Billboard hits, 1959 to 2020. Strip out the lyrics, strip out the genre label, keep only the audio profile - and you can still tell which songs mention alcohol.

Ambient drinking cues are easy to underestimate. Music is the obvious one: it shapes what you expect from an evening before you've consciously decided anything. What made me stop on this paper is that the link between party sound and alcohol-themed lyrics sits in the audio itself.

What they did

Researchers analyzed 6,110 songs from the Billboard Hot 100 released between 1959 and 2020. For each track they pulled Spotify audio features: danceability, speechiness, energy, valence, acousticness, liveness, instrumentalness, loudness, tempo, and mode. Logistic regression then tested which of those features predicted whether the lyrics contained alcohol references.

The theoretical frame is Uses and Gratifications Theory: people actively choose media to satisfy psychological and social needs. The authors' premise - party contexts pull toward a specific sound profile and toward alcohol-themed lyrics at the same time, because both serve the same social function. If that holds, sound and lyric content should line up in a systematic pattern.

They do.

What they found

Alcohol references appeared in 16.1% of songs, and prevalence rose significantly across the 60-year window.

Audio features predicting higher odds:

  • Danceability (OR = 1.35) - stronger beat, more rhythmic pull
  • Speechiness (OR = 1.39) - the strongest single predictor in the model; vocal-heavy, rap-adjacent tracks, the ones where words carry the song rather than melody
  • Liveness (OR = 1.09) - audible crowd energy in the recording
  • Positive valence (OR = 1.11) - emotionally upbeat
  • Major key (OR = 1.18) - minor-key songs skew away

Higher acousticness (OR = 0.82) and instrumentalness (OR = 0.85) went the other way. Loudness, tempo and raw energy weren't significant.

What it means

Put those features together and you get the party track: danceable, crowd-sounding, bright, vocal-heavy, major key. That matches intuition. Odds ratios across 6,000 hits are harder to argue with than a feeling.

The surprise sits at the bottom of the list. Loudness, tempo, raw energy - all insignificant. Intensity doesn't discriminate. Social texture does: vocal character, rhythmic feel, live energy.

Speechiness is the number I kept coming back to. Hip-hop and rap name specific drinks more than any other genre, and they also top Spotify's speechiness scale. Genre isn't in the model directly. Speechiness is doing that work, and at OR = 1.39 it beats everything else in there.

Liveness is worth a moment too. Songs that sound like live recordings - crowd noise, performance energy - mention alcohol more often. Makes sense: live venues and drinking go together constantly. The music that catches that social energy apparently catches the language around it.

The rising prevalence over six decades probably reflects genre shifts more than broad cultural drift. 1959 to 2020 is exactly the stretch where hip-hop moved from the margins to the dominant commercial form.

For one listener with a playlist on, this is background noise rather than a warning. A playlist built around high danceability and bright energy carries more alcohol references than you'd guess while you're focused on the conversation.

The researchers' practical goal is a surveillance tool: scan large music libraries, flag songs for lyric review, skip the manual checking. Useful for public health monitoring. The model isn't validated for that yet, and the Billboard sample skews toward commercial mainstream.

One limit matters. The study doesn't separate songs that glorify drinking from songs that mention it in passing, and those are different kinds of exposure. Everything here is correlational, no behavior-change claim anywhere in the paper, so that distinction stays open.

Source: Alcohol and Alcoholism, 10.1093/alcalc/agag041