What can Machine Learning do for Literary Critics?

First in a series of posts about artificial intelligence sparked by “The Great AI Awakening,” an article from December 2016 by Gideon Lewis-Kraus in the New York Times Magazine. Cross-posted to Michael Ullyot‘s blog.

Can you trust machines to make decisions on your behalf? You’re doing it already, when you trust the results of a search engine or follow directions on your phone or read news on social media that confirms your worldview. It’s so natural that you forget it’s artificial; someone programmed a machine to make it happen. If Arthur C. Clarke is right (“any sufficiently advanced technology is indistinguishable from magic”), we’re living in the age of magical thinking.

Read more

Extraordinary Language

Screen Shot 2014-03-03 at 18.00.46 What makes poetry poetic? It’s a question as old as criticism itself, which probably got its start during the recitation of the world’s first poem. What makes its language different from any other?

It’s not rhyme, because unrhymed blank verse seems poetic enough. What about form? Or meter — the limited number of syllables before a line breaks? Or the pattern of those syllables? Maybe, but there are plenty of prose passages in Shakespeare that seem to qualify as poetry. “What a piece of work is a man,” Hamlet says in prose, but not prosaically: “how noble in reason; how infinite in faculties, in form and moving; how express and admirable in action,” and so on.

Read more

Nine Lessons of Project Management

This summer I (Michael Ullyot) went to the Digital Humanities Summer Institute (DHSI) at the University of Victoria, where digital humanists take seminars, participate in unconferences, and give colloquium papers. This was my second visit to DHSI, whose mashup of “skills workshop, international conference, and summer camp” captures the digital-humanities ethos. The official program ranges from text encoding to augmented reality — subjects they didn’t cover in graduate school. All the while, there are informal opportunities for learning: a lively Twitter backchannel, an unconference, and philosophical musings over drinks: coffee in the morning; beer in the evening; rinse and repeat.

Read more

Research Assistant(s) Wanted

Dr Michael Ullyot is hiring 1-2 research assistants for the 2013-14 academic year to work on a digital humanities research project. The Zeugmatic is a text-analysis tool to automate the detection of rhetorical figures — particularly, patterns of repetition and variation in Shakespeare’s language. (For details, see < http://zeugmatic.org/about/ >.) Candidates must be in Calgary from mid-August for ~ 15 hrs / wk; and from September onward for ~ 5 hrs / wk.

Read more

Civil Engineering


By Michael Ullyot

The Zeugmatic is in Victoria, BC this week for two meetings, the Canadian Society for Digital Humanities (part of the Congress of the Humanities and Social Sciences) and the Digital Humanities Summer Institute. This is the first in a series of reports.

I (Michael Ullyot) met today with Randy Harris about RhetFig, his seed database of about 500 rhetorical figures that does many of the things our project’s taxonomy of figures began to do — as Maria Jaramillo wrote about last month.

Read more


By Michael Ullyot

My project for Summer 2013 is to design a text-analysis algorithm capable of recognizing Shakespeare’s rhetorical figures. For instance, this1 repetition of “farewell” in Othello is called an anaphora:

2013 03 28 12 39 39

That’s a pretty straightforward anaphora, and is just the kind of linguistic feature that a pattern-recognizing algorithm could detect. I could show you more complicated examples, but first let’s imagine the higher-order interpretations that this algorithm would enable.

Read more

  1. Wales, Katie. “An A-Z of Rhetorical Terms.” in Sylvia Adamson, Lynette Hunter, et al. (eds.) Reading Shakespeare’s Dramatic Language: A Guide. London: Arden Shakespeare, 2001. 271-301; 278. Photo with Crossprocess (app) by the author. []