Keywords: literary studies, computational linguistics, OCR correction
This poster (size A0) presents our project, A Question of Style: individual voices and corporate identity in the Edinburgh Review, 1814-1820, which is funded by a Research Society for Victorian Periodicals Field Development Grant running until October 2017.
We want to assess the assumption that early nineteenth-century periodicals succeeded in creating, through a “transauthorial discourse”, a unified corporate voice that hid individual authors behind an impersonal public text (Klancher 1987).
We are creating a sample corpus of approximately 500,000 words comprising 325,000 words from the Edinburgh Review and 175,000 from its competitor, the Quarterly Review, for a total of about 80 articles. To assist our OCR correction, metadata creation and textual markup, we are developing a suite of Python scripts, based on our previous work with post-OCR correction (King 2013) and semi-automated TEI markup (Willis et al 2010).
We employ methods from periodical studies, book history, computational linguistics and computational stylistics to “operationalise” our definition of style in order to select features that can be measured empirically, transforming concepts into a set of operations (Moretti 2013). We will focus on features at the level of words and sentences such as: vocabulary richness, length of articles, length of sentences, length of quotations from text under review, distribution of parts of speech, distinctive vocabulary of each journal, distinctive vocabulary of each author, distinctive vocabulary in each type of review (literature, travel, politics etc.), using methods such as term frequency: inverse document frequency, Burrows’ Delta and Zeta methods, Moretti’s Most Distinctive Words Method, and Principal Component Analysis.
Finally, we will qualitatively describe the results of this stylistic analysis and evaluate them within the context of both literary scholarship on nineteenth-century periodicals and computational linguistics scholarship, using our literary and historical interpretation to generate critical knowledge out of our measurements. [297 words]
Works Cited
King, David. “Digging in the library.” Invited lecture presented at Biodiversity Informatics Horizons 2013, Rome. September 2013
Klancher, Jon P. The Making of English Reading Audiences, 1790-1832. University of Wisconsin Press, 1987.
Moretti, Franco. “Operationalizing”: or, the function of measurement in modern literary theory” Stanford Literary Lab. Pamphlet 6. Stanford Lit. Lab, December 2013.
Willis, Alistair, David King, David Morse, Anton Dil, Chris Lyal, and Dave Roberts. “From XML to XML: The why and how of making the biodiversity literature accessible to researchers.” Language Resources and Evaluation Conference (LREC), Valletta. May 2010.