Text Mining: The Long Walk


Now that we’ve established that there is a link between key scenes in the plot progress of a Stephen King novel and mapped sentiment peaks coded from the text, we can spend significantly less time on analyzing each peak to show this. This will allow us to go through books with a little less ponderous text.

The Long Walk (1979)

The Long Walk is another short Bachman novel about sexually frustrated young men. This time it’s about the contestants of a gruelling, cruel national sport instituted after America’s loss in the Second World War and the institution of military rule by “The Squads.” The backdrop is briefly described but evocative for that when it is mentioned. At any rate, the protagonist is one of 100 contestants who start the Long Walk. They have to keep walking at a certain speed or they are shot by soldiers who are driving around beside them. They get three warnings to get their speed back up, otherwise the guns ring out and down goes another contestant. It’s a pretty horrifying idea when it comes right down to it, if only for how weirdly plausible it is given the modern love of both spectacle and fascism. It’s also pretty psychologically taxing, especially once the weakest contestants die off and it becomes a game to walk your opponents into the ground.


As you can see from the soundwave graph, this one is pretty front-loaded in terms of sentiment. A lot of this I think is because of the structure of the game of the Long Walk. The book is loaded emotionally at the front because the majority of the contestants die off in the first half of the book; the second half then becomes a psychological competition between the remaining contestants, who dwindle right down to the end.


Warning is clearly the biggest emotional factor and that’s pretty natural when you consider the text. The soldiers riding along on the halftrack next to the contestants (“the squads”) shout out “Warning!” to the contestants when they slow down to an unacceptable speed, or collapse, or in any other way stop walking at the right speed. “Dead” and “die” are pretty self-explanatory as well, since that’s what most of the characters in the book end up doing. “Pretty” is interesting as well, since there is a barely-contained frustrated sexual subtext flowing under the contest; it’s all men, and women are used by them as goads, prizes, and soothing dreams. Like Rage, it’s a weird, gleeful anger at society, and by society we mean “lack of sex.” Richard Bachman – King’s id, perhaps – is the original Incel Prophet.


Here’s what we have as a smooth-line graph. We bottom out in the second quarter of the book and then generally go up – after confronting a fear of death, our survivors turn their thoughts to winning, or at least winning by outlasting their enemies.

Stats for this one:

Negative Peak: -81

Maximum Peak: 5

Median: -29.5

Mean: -34.78



Interesting that the final chapter is a positive sentiment peak, even if it is barely above zero. Also in 4 they discuss necrophilia and someone buys a ticket but they also discuss how glad they are to be alive, even though 89 more of them will die.


5-8 feature a lot of dead people. Then there’s a lull, and more people die but with less frequency. Then a bunch of very ugly deaths happen in 16 leaving 9 to go – the core cast of the book. You can honestly plot out the course of the Long Walk in terms of how the event is going by mapping the sentiment like this.

At any rate, The Long Walk seems to be a textbook example of how you can show the progression of a novel using sentiment analysis on text and graphing it. In terms of what we can learn about King’s style or about fiction in general, remains to be seen much later.


One thought on “Text Mining: The Long Walk

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s