Independence day is just a few days away so I spent a bit of time over the weekend digging into the data to see what are the most listened to songs on the Fourth of July. Eliot wrote a great piece about the data for the Spotify Blog: The Most Distinctive Fourth of July Songs in the 50 U.S. States. Here I dig in a bit deeper.
From a musical perspective, The Fourth of July is a very interesting holiday. It’s a big summer outdoor party – and the music reflects that. On the Fourth, people listen to patriotic songs, BBQ songs, popular songs, party songs, songs about place and history. People listen to wide range of genres, from rock and pop to folk, country, marches, and new weird america. To see what music people listen to on the Fourth I went through about 5,000 playlists that people have created that have ‘fourth of july’ in the title. I aggregated the songs across all of these playlists and created a playlist of the top 100 or songs.
As you can see, the playlist is a mix of US-centric music and summer party music – which is a pretty good reflection of what people actually listen to on the Fourth of July. But I wanted to go a bit further and see what music was particularly distinctive for the Fourth of July – as compared to any other summer outdoor party playlist. To do this, I collected the top most frequently appearing songs on the Fourth of July playlists and scored each song by calculating the ratio of the play counts that occurred on July 4, 2013 in the U.S. vs. play counts for the song during the following weeks. Songs that were played much more frequently on the Fourth than during the rest of July get a much higher score. Ranking songs by this ratio yields the list of distinctive Fourth of July Songs:
I think it is a pretty good list of the music that we listen to more on the Fourth of July than on any other day. There’s a John Philip Sousa march, Woody Guthrie’s This Land is Your Land, Katy Perry’s Firework, lots and lots of country music. Some artists appear more frequently than others – Bruce Springsteen, John Mellencamp and Lee Greenwood are Fourth of July favorites.
I’m always interested in regional differences in how we listen to music, so I looked at the listening in each state in the U.S. to see which of the core Fourth of July songs was listened to more. If you look just at the most popular Fourth of July song in each state the results are pretty boring – the most popular song in 46 out of 50 states for July 2013 was Party in the USA by Miley Cyrus – but if you look at the distinctive score (the ratio of plays on the fourth to plays during the following weeks), you get a more nuanced view of how people listen to music. Of course we represent this as a map:
So the real question is, are these playlists generated by data mining any good? As actual playlists to listen to, I don’t think so. They are too incoherent, with jumps that take you from a sappy country song, to a teen pop song, to a march that will give you iPod whiplash. Compare the playlists above to a human-curated Fourth of July Playlist:
This is a much more listenable playlist. However, I think the data mined playlists do provide an excellent starting point – a big pool of Fourth of July songs. With a genre and popularity filter these could be turned into decent, listenable playlists. Similarly, give this pool of Fourth of July songs to a team of music curators and they can build some pretty fantastic Fourth of July playlists for every type of music fan.