Beyond Search: Literary Studies and the Digital Library

The papers in this session are derived from the collaborative
research being conducted in the “Beyond Search and Access:
Literary Studies and the Digital Library” workshop at
Stanford University. The workshop was set up to investigate
the possibilities offered by large literary corpora and how
recent advances in information technology, especially machine
learning and data-mining, can offer new entry points for the
study of literature. The participants are primarily interested in
the literary implications of this work and what computational
approaches can or do reveal about the creative enterprise. The
papers presented here share a common interest in making
literary-historical arguments based on statistical evidence
harvested from large text collections. While the papers are
not, strictly speaking, about testing computational methods
in a literary context, methodological evaluations are made
constantly in the course of the work and there is much to
interest both the literary minded and the technically inclined.