Abstract
The statistical analysis of literary texts has yielded valuable results, not least when it has treated of the frequency patterns of very common words. But, whereas particular frequency patterns have usually been examined as discrete phenomena, it is possible to correlate the frequency profiles of all the very common words, to subject the resulting correlation matrix to eigen analysis, and to present the results in graphic form. The specimens offered here deal, first, with differences among Jane Austen's characters and, secondly, with differences between authors. The most striking general differences among the authors studied relate to historical eras and authorial gender.
Similar content being viewed by others
Author information
Authors and Affiliations
Additional information
John Burrows has been Professor of English at the University of Newcastle, N. S. W. since 1976. He was Commonwealth Fellow of St. John's College, Cambridge in 1979-80 and a Visiting Research Fellow at the Institute for Advanced Studies in the Humanities at the University of Edinburgh in 1988. His earlier publications are mostly in the field of Australian literature. His chief research interest since 1979 has been in the computer-assisted analysis of literary texts. Publications in this field include:Computation into Criticism: A Study of Jane Austen's Novels and an Experiment in Method (Oxford, Clarendon Press, 1987); “The Reciprocities of Style: Literary Criticism and Literary Statistics, ” Essays and Studies, n. s. XXXIX (1989), 78–93. He is currently preparing for the Clarendon Press a further book with the working titlePatterns in Rough Ground: a Computer-assisted Study of the Language of Narrative.
Rights and permissions
About this article
Cite this article
Burrows, J.F. ‘An ocean where each kind. . .’: Statistical analysis and some major determinants of literary style. Comput Hum 23, 309–321 (1989). https://doi.org/10.1007/BF02176636
Issue Date:
DOI: https://doi.org/10.1007/BF02176636