Date of this Version
Published in Digital Scholarship in the Humanities, Vol. 33, No. 4 (2018), pp 821–844.
This research examines and contributes to recent work by Matthew Jockers and Gabi Kirilloff on the relationship between gender and action in the nineteenth-century novel. Jockers and Kirilloff use dependency parsing to extract verb and gendered pronoun pairs (“he said,” “she walked,” etc.). They then build a classification model to predict the gender of a pronoun based on the verb being performed. This present study examines the novels that were categorized as outliers by the classification model to gain a better understanding of the way the observed trends function at the level of individual narratives. We argue that while the classifier successfully categorized and identified novels in which characters behave unconventionally—that is, in ways not typical to the corpus as a whole— the rhetorical effects of these unconventional novels (and the extent to which their authors openly question nineteenth-century gender norms) vary based on other factors of characterization and narration. We propose that the combination of machine and human reading that this essay utilizes provides a productive model for allowing distant reading to guide and provoke traditional humanities scholarship.