Table of Contents
Fetching ...

Does Burrows' Delta really confirm that Rowling and Galbraith are the same author?

Boris Orekhov

TL;DR

This study scrutinizes whether Burrows' Delta can reliably attribute The Cuckoo's Calling to J.K. Rowling by re-evaluating Delta with genre-appropriate corpora. It constructs two contrastive corpora (contemporary detective fiction and modern fantasy) and analyzes them with the stylo package, comparing Delta results to an imposters-based attribution method. Delta yields inconsistent conclusions depending on genre and dataset, while the imposters algorithm consistently supports Rowling as the author across contexts. The work highlights the importance of dataset design and cross-method validation in stylometry, suggesting that imposters can provide a more robust attribution signal and that broader, cross-language tests are warranted for generalization.

Abstract

The stylo package includes a frequency table that can be used to calculate distances between texts and thus independently solve the problem of attribution of The Cuckoo's Calling, a novel that J.K. Rowling said she wrote. However, the set of texts for this table is very vulnerable to criticism. The authors there are not modern, they wrote in a different genre. I set out to test the performance of the method on texts that are more relevant to the research question.

Does Burrows' Delta really confirm that Rowling and Galbraith are the same author?

TL;DR

This study scrutinizes whether Burrows' Delta can reliably attribute The Cuckoo's Calling to J.K. Rowling by re-evaluating Delta with genre-appropriate corpora. It constructs two contrastive corpora (contemporary detective fiction and modern fantasy) and analyzes them with the stylo package, comparing Delta results to an imposters-based attribution method. Delta yields inconsistent conclusions depending on genre and dataset, while the imposters algorithm consistently supports Rowling as the author across contexts. The work highlights the importance of dataset design and cross-method validation in stylometry, suggesting that imposters can provide a more robust attribution signal and that broader, cross-language tests are warranted for generalization.

Abstract

The stylo package includes a frequency table that can be used to calculate distances between texts and thus independently solve the problem of attribution of The Cuckoo's Calling, a novel that J.K. Rowling said she wrote. However, the set of texts for this table is very vulnerable to criticism. The authors there are not modern, they wrote in a different genre. I set out to test the performance of the method on texts that are more relevant to the research question.
Paper Structure (5 sections, 6 figures, 2 tables)

This paper contains 5 sections, 6 figures, 2 tables.

Figures (6)

  • Figure 1: Cluster analysis of the data included in stylo.
  • Figure 2: Cluster analysis of the detective data.
  • Figure 3: Cluster analysis of the fantasy data.
  • Figure 4: Distribution of stylometric distances in detective fiction corpus.
  • Figure 5: Distribution of stylometric distances in fantasy fiction corpus.
  • ...and 1 more figures