Where did the English novel come from? Experimenting with computational approaches to explore language in 17th Century prose fiction
Project Overview
The project investigated the linguistic properties that characterise the forming of the new cultural object, the novel, during a heterogenous and experimental era for literary fiction. It works to track the evolution of language, specifically language used in narrative communication to understand how the genre emerged. The project included collecting text-based data (at times experimenting with optical character recognition tools), applying and evaluating data cleaning techniques and how these may incorporate AI, data tagging and extraction using TEI XML and BBEdit, corpus based analysis and more.
What were the key results of your research project?
- - Creating machine-readable text-based data by encoding four 17th century novels using TEI XML, tagging the texts by Headers, Front Matter, instances of foreign languages, characters who speak, speech (differentiating direct and indirect, character and gender) and structural elements such as letters or poems within a text. This enabled me to track and consider the distribution of speech across gender and character.
- Experimenting with Optical character recognition tools and then creating and trailing AI master prompts for data cleaning on AI to consider how efficient it can be.
- Experimenting with spaCy Natural Language Processing (NLP) Python code on the corpus of 17th century novels collected. Also code that converts the encoded texts into plain text to so that the NLP tools would work better.
- Beginning an investigation into gendered transitivity analysis (that can be continued) that revealed patterns about how men and women are represented as participants in clauses. This included creating dependency parser visualisations (using spaCy) of concordance lines surrounding the gendered pronouns "she" and "he" to show the grammatical relationships in sentences and justify the categorisation of transitivity. Creating categorising, visualising and analysing this data.
link to embed YouTube video
How do you feel you have benefitted from completing this internship and has it made you consider future career paths?
Studying the humanities, I often close myself off from the idea that I could ever pursue anything in the technology. So, this internship has been the perfect opportunity to push myself out of my comfort zone familiarise myself with a range of computational skills I never thought I would have the opportunity to acquire. The internship created an amazing learning environment, in which I got to learn coding and technical skills practically with research professionals there to help and support you along the way. I got to be involved in proof- of concept research which I am fascinated by and it opened up a completely different technological side of my subject, English Language and Literature. It has made me consider the plethora of options to pursue integrating English and research software engineering that I can apply both in my future study and future career.
Download presentation slides