• Machine Learning and Human Perspective

    Author(s):
    Ted Underwood (see profile)
    Date:
    2020
    Group(s):
    2020 MLA Convention, Digital Humanists, GS Speculative Fiction, TC Digital Humanities
    Subject(s):
    Machine learning, Hermeneutics, Speculative fiction, Science fiction, Fantasy, Digital humanities
    Item Type:
    Article
    Tag(s):
    distant reading
    Permanent URL:
    http://dx.doi.org/10.17613/fzf7-tm48
    Abstract:
    Numbers appear to have limited value for literary study, since our discipline is usually more concerned to explore differences of interpretation than to describe the objective features of literary works. But it may be time to re-examine the assumption that numbers are only useful for objective description. Machine learning algorithms are actually bad at being objective, and rather good at absorbing human perspectives implicit in the evidence used to train them. To dramatize perspectival uses of machine learning, I train models of genre on groups of books categorized by historical actors who range from Edwardian advertisers to contemporary librarians. Comparing the perspectives implicit in their choices casts new light on received histories of genre. Scientific romance and science fiction—whose shifting names have often suggested a fractured history—turn out to be more stable across two centuries than the genre we call fantasy.
    Notes:
    cite: Ted Underwood, “Machine Learning and Human Perspective,” in “Varieties of Digital Humanities,” coordinated by Alison Booth and Miriam Posner, PMLA 135.1 (January 2020): pp. 92-109.
    Metadata:
    Published as:
    Journal article    
    Status:
    Published
    Last Updated:
    7 months ago
    License:
    Attribution
    Share this:

    Downloads

    Item Name:pdf machine-learning-and-human-perspective-postprint.pdf
     Download View in browser
    Activity: Downloads: 305