{"id":157,"date":"2022-03-01T12:03:20","date_gmt":"2022-03-01T19:03:20","guid":{"rendered":"http:\/\/briancroxall.net\/w22dh\/?page_id=157"},"modified":"2022-03-01T13:11:12","modified_gmt":"2022-03-01T20:11:12","slug":"topic-modeling-peanuts","status":"publish","type":"page","link":"https:\/\/briancroxall.net\/w22dh\/assignments\/topic-modeling-peanuts\/","title":{"rendered":"Topic Modeling Peanuts"},"content":{"rendered":"

Rationale<\/h2>\n

We recently finished our reading of the first volume of The <\/em>Complete Peanuts<\/em>. We\u2019ve read some of it closely thanks to your daily comics discussions<\/a>, and we\u2019ve gotten an even closer look at a subset of those strips as we\u2019ve\u00a0marked them up with TEI and CBML<\/a>. With all of this behind us, I\u2019m guessing that we could offer some pretty in-depth takes on what\u00a0Peanuts<\/em> is \u201cabout.\u201d And yet, we have only read 4% of his 17,897 strips. So any pronouncements about what Peanuts<\/em>\u00a0is \u201cabout\u201d at this point would necessarily require ignoring most of the available evidence.<\/p>\n

Fortunately, digital humanities methods offer us, as Robert K. Nelson writes<\/a>, “an additional method that allows us to examine and detect patterns within not a sampling but in the entirety of an archive.” One of these methods is topic modeling. From our reading, we know that topic modeling is, as Megan Brett puts it<\/a>, \u201ca way of identifying patterns in a corpus\u201d by using an unsupervised machine-learning process to find \u201crecurring pattern[s] of co-occurring words.\u201d In other words, topic modeling should help us discover some of the underlying discourses within the whole\u00a0Peanuts<\/em>\u00a0corpus, that thing we could never, ever read in a regular semester.<\/p>\n

Of course, it needs to be said that topic modeling works with text and text only. And, as we all know at this point,\u00a0Peanuts<\/em>\u00a0is about\u00a0so much more<\/em> than dialogue and diegetic text. This method cannot even pretend to account for the visual aspect of Schulz\u2019s work. Nevertheless, in our quest to understand Peanuts<\/em>\u2014and especially how it might change over time\u2014topic modeling provides us with a chance to consider patterns of linguistic affinity and difference that are invisible simply because of their scale. In short, while we know that topic modeling cannot be the final word about\u00a0Peanuts<\/em>, it\u2019s still worth a shot!<\/p>\n

Nitty Gritty<\/h2>\n

For this assignment, you will collectively produce several topic models of the text of Schulz\u2019s strips and begin the process of analyzing them. The assignment has one outcome: a collaboratively written Google Doc. This Doc is due at the end of class on Tuesday, 8 March<\/strong>.<\/p>\n

Step One: Get the Data<\/h3>\n

You can find the cleaned GoComics Peanuts<\/em>\u00a0data in our repository in the\u00a0gocomics\/peanuts-clean<\/code>\u00a0folder<\/a>. Please remember that these data are copyrighted: while we are using them in a fair-use context (a research project and an educational experience), they should not be distributed outside of the class.<\/p>\n

Step Two: Predict the Data<\/h3>\n

Spend a little time thinking about what you’re likely to see in your topic model. Jot down your thoughts in a shared Google Doc (see Step Six) so you don’t lose track of them. In many ways, this is sort of like the “hypothesis” step in that science project you did in middle school.<\/p>\n

Step\u00a0 Three: Model the Data<\/h3>\n

Using MALLET and the Step-by-Step Guide to Topic Modeling<\/a>, collectively make at least 6\u00a0different topic models of the corpus<\/strong>. Experiment with changing some or all of the following:<\/p>\n