Computational Stylistics and the Bronte Sisters

Following Jane Austen’s literary triumph in the Georgian Era, the ensuing Victorian Era saw the emergence of phenomenal works from female writers such as George Eliot (real name Maryanne Evans) and the Bronte sisters: Charlotte, Emily, and Anne.  Although many scholars and academics question the gender based difference, if any, between male and female styles of writing during the period, I was interested in analysing how stylistically similar the Bronte sisters were in their individually accomplished works. Having been introduced to Computational Stylistics in my digital humanities seminar I was able to analyse the collective corpus of the Bronte sisters in a matter of moments and found some interesting results.

Initially, I ran the following novels through R:

  • Emily Bronte. Wuthering Heights (1847)
  • Charlotte Bronte. The Professor (Published in 1857 but written before Jane Eyre)
  • Charlotte Bronte. Jane Eyre (1847)
  • Charlotte Bronte. Shirley (1849)
  • Charlotte Bronte. Villette (1853)
  • Anne Bronte. Agnes Grey (1846)
  • Anne Bronte. The Tenant of Wildfell Hall (1848)

A cluster analysis of the novels produced the following results:


The computational analysis successfully clustered the novels together according to the specific Bronte sister who wrote them thereby indicating the unique authorial style of each writer; Charlotte Bronte’s four novels appear together in green, Emily’s only novel in Blue, and Anne Bronte’s novels in red. Moreover, the graph indicates that Emily Bronte’s style is more similar to her older sister Charlotte’s than that of her younger sister Anne’s.

In order to gain a more comprehensive perspective I began to consider other notable Victorian female authors whose authorial style I could compare to the Bronte’s collective corpus. I chose Jane Austen, whose work preceded the Bronte’s, and George Eliot who published novels shortly after the Bronte’s. Following the initial cluster analysis I added the following novels to the Bronte collection to be analysed by R:

  • Jane Austen. Emma (1815)
  • Jane Austen. Sense and sensibility (1811)
  • Jane Austen. Northanger Abbey (1818)
  • Jane Austen. Pride and Prejudice (1813)
  • Jane Austen. Mansfield Park (1814)
  • George Eliot. Adam Bede (1859)
  • George Eliot. Middlemarch (1871/72)
  • George Eliot. Silas Marner (1861)
  • George Eliot. The Mill on the Floss (1860)

Adding the work of fellow 19th century female authors had a considerable effect on the cluster analysis. Jane Austen’s novels cluster together in red, George Eliot’s novels in blue and the Bronte’s in green.


The inclusion of other 19th century female authors causes the software to cluster the Bronte sisters together, indicating a notably similar style within their collective corpus. As before, the data illustrates that Emily Bronte’s authorial style is more similar to that of Charlotte Bronte than to Anne Bronte.  A consensus tree analysis of the same collection of novels offers similar results


Austen’s work branches off from the other authors indicating a unique style of writing and a prominent authorial signature within her work.  Austen’s work splits into subsequent branches perhaps illustrating her distinct style in use within various genres and allowing for a progression in authorial style over time. Similarly, George Eliot’s work assembles as a collection very similar in style, demonstrating an individual authorial signature is prominent within her work. The Bronte’s, however, cluster together and appear almost like a singular author with malleable style rather than three separate authors with a distinct style.

Although the data indicates remarkably similar styles between the Bronte sisters it is another challenge to analyse why this similarity occurs. Perhaps the sisters share a similar style because of genetic predisposition, shared reading material, and shared environments during childhood development.  Perhaps both Emily and Anne were heavily influenced by their older sister Charlotte’s work and therefore mimicked her style, or, more intriguing, perhaps the Bronte’s collaborated on their novels. This of course is speculative and much more close-reading and analysis is required to produce a more conclusive answer as to why Bronte’s collective work shares such similar style, however, the computational data alone is certainly thought provoking.

One response

  1. Pingback: #9: Agnes Grey by Anne Brontë (Catharina) | classicbookchallenge

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s