Unnatural Language and Natural Thinking: Shakespeare and His Contemporaries

Critics of computational text analysis tend to perceive its focus on language patterns as a flattening of qualitative texts into quantifiable patterns. They’re right. But a text’s linguistic operating system deserves close scrutiny when it reveals features of the text that a human reader can’t perceive, or when it flags evidence beyond our capacity to gather. The Augmented Criticism Lab has developed algorithms to detect features of repetition and variation in the works of Shakespeare and his contemporaries (starting with drama, namely the Folger’s Digital Anthology). We’ve begun with features like rhetorical figures that repeat lemmas (heed, heedful, heeding) or morphemes (heeding, wringing, vexing). We use natural-language processing to gather evidence of these unnatural formulations, to ask whether they signal natural habits of thought. The interpretive payoff is our ability to make more definitive arguments not just about these figures, but also about underlying cognitive habits. This presentation describes our process and our corpus, and presents a range of our results with this initial corpus before we expand to the billion words in the EEBO-TCP corpus (1473-1700). Presented by MARCS: Medieval and Renaissance Cultural Studies Research Group
Location:
Social Sciences 1015
Speaker:
Michael Ullyot, associate professor, Department of English, University of Calgary
More information at http://www.ucalgary.ca/events/calendar/unnatural-language-and-natural-thinking-shakespeare-and-his-contemporaries