Distinguishing Voices in <I>The Waste Land</I> using Computational Stylistics. Brooke, J., Hammond, A., & Hirst, G. Linguistic Issues in Language Technology, 12(2):1--41, 2015.
Distinguishing Voices in <I>The Waste Land</I> using Computational Stylistics [link]Paper  abstract   bibtex   
T. S. Eliot's poem The Waste Land is a notoriously challenging example of modernist poetry, mixing the independent viewpoints of over ten distinct characters without any clear demarcation of which voice is speaking when. In this work, we apply unsupervised techniques in computational stylistics to distinguish the particular styles of these voices, offering a computer's perspective on longstanding debates in literary analysis. Our work includes a model for stylistic segmentation that looks for points of maximum stylistic variation, a k-means clustering model for detecting non-contiguous speech from the same voice, and a stylistic profiling approach which makes use of lexical resources built from a much larger collection of literary texts. Evaluating using an expert interpretation, we show clear progress in distinguishing the voices of The Waste Land as compared to appropriate baselines, and we also offer quantitative evidence both for and against that particular interpretation.
@article{BrookeLiLT,
 author = "Julian Brooke and Adam Hammond and Graeme Hirst",
 title = "Distinguishing Voices in <I>The Waste Land</I> using Computational Stylistics",
 year = "2015", 
 volume = "12", 
 number = "2", 
 pages = "1--41",
 journal = "Linguistic Issues in Language Technology",
 url = "http://csli-lilt.stanford.edu/ojs/index.php/LiLT/article/view/55",
 abstract = "T. S. Eliot's poem <I>The Waste Land</I> is a notoriously
                  challenging example of modernist poetry, mixing the
                  independent viewpoints of over ten distinct
                  characters without any clear demarcation of which
                  voice is speaking when. In this work, we apply
                  unsupervised techniques in computational stylistics
                  to distinguish the particular styles of these
                  voices, offering a computer's perspective on
                  longstanding debates in literary analysis. Our work
                  includes a model for stylistic segmentation that
                  looks for points of maximum stylistic variation, a
                  k-means clustering model for detecting
                  non-contiguous speech from the same voice, and a
                  stylistic profiling approach which makes use of
                  lexical resources built from a much larger
                  collection of literary texts. Evaluating using an
                  expert interpretation, we show clear progress in
                  distinguishing the voices of <I>The Waste Land</I>
                  as compared to appropriate baselines, and we also
                  offer quantitative evidence both for and against
                  that particular interpretation.",
 }

Downloads: 0