How Generative AI can Enable Students to Explore the Impact of Linguistic Choices on Literary Works
Generative AI & the Impact of Linguistic Choices on Literary Works
Lecturer - Dr Chris Fitzgerald |
---|
Discipline - English Language and Literature |
Subject - Language and Literature |
Level - Undergraduate |
Class Size - Small group |
Mode of Delivery - In-person |

In this case study, Dr Chris Fitzgerald explains how he used ChatGPT to alter open access literary texts so that students could see both the ability of generative AI to achieve this and how small alterations can significantly change a literary work. Though he used ChatGPT as it is the most well-known large language model (henceforth LLM) and is free to use, other tools such as claude.ai may produce similar results. This helped students to see the impact of linguistic choices on literary work, which is a core objective of the module. After modelling the approach, students then used the tool to perform similar alterations.
Rationale
In our classes, we discuss subjects like narrative and dialogue. We investigate how, for example, the third person works for certain narratives, while the first person is more effective in others. To really observe how this effects a narrative, I wanted to manipulate popular literary works to change the narrative stance from one person to another or to change a work from a reliable to an unreliable narrator. In addition, I wanted my students to notice what language changes would be necessary to achieve this. I discovered that the use of a LLM tool would be helpful in this regard.
Description of the Teaching and Learning Approach

The emergence of various AI tools such as ChatGPT is causing valid concern for educators in various disciplines. For example, there is much anxiety surrounding how students might use them to produce assessment tasks that look like they may have been self-produced. However, these tools also present abundant opportunities for educators, which should not be neglected due to the apparent dangers that may be posed by generative AI tools. The approach outlined here is one example of how LLM AI tool, ChatGPT can be used to deepen students’ understanding of both linguistics and literature.
Students on the English Language and Literature programme get input from both Linguistics and Literature modules with the common ground being the linguistic analysis of literary texts and how authors use language to achieve certain stylistic outcomes. ChatGPT has the capacity, in a matter of seconds, to take well known literary texts and manipulate them so that these linguistic choices can be altered throughout a text. For example, the novel, The Catcher in the Rye is well known for how the author JD Salinger employs certain linguistic devices to present the narrator, Holden Caulfield as unreliable. By taking an extract of a text like this, or, if the entire text if it is openly accessible, and prompting ChatGPT to change the narrator to be a reliable one, students can see both how this effects the text and how this is linguistically achieved. This often results in students noticing and appreciating the language choices of the author in a new way.
ChatGPT (and other LLMs) rely on prompts from the user to instruct it to perform requested tasks. Prompts should be as precise and specific as possible. Prompts can also include sample texts, which is important for this task. For the above example, I copied and pasted in the opening paragraphs of The Catcher in the Rye and added the prompt: change this text so that the narrator is reliable. The LLM then produces a text that is adjusted to present the narrator as reliable. In this case, this is achieved by making the narrative clearer and more coherent and less fractured. If the resultant text is not satisfactory, then the user can add more prompts to further alter the text, for example, make it more realistic. This process can continue indefinitely or until the LLM responds with a statement of inability to perform a request.
What Worked and Why?

The ease and efficiency of this is very effective. After initial demonstration, students are able to manipulate texts themselves and experiment with different aspects of texts of their choosing. By observing the shifts in language use that achieve different literary stylistic choices (such as the use of first-person pronouns to create a first-person narrative), students familiarised themselves with the effect of these choices on literary work and were able to think more critically about alternatives to these choices and their effects.
Any problems or issues that arose from this approach?
There is a certain hesitance when attempting to alter masterpieces, but the provision of a caveat that this is experimental is sufficient to allay these worries. In addition, there may be some barriers to access as Chat GPT requires the creation of an account, but all of my students already had accounts. Other generative AI tools such as co-pilot, which is licensed through MIC students’ accounts, may be a good alternative if such issues arise.
Tips for Implementation

ChatGPT is still prone to ‘hallucinations’ so it does not perfectly achieve its goals, so it is advisable to check the texts it produces in advance. I gave examples of such results
generated by ChatGPT to students for them to see and be able to detect these in their own experiments. Though this case study exemplifies the use of ChatGPT for the generation of texts in language and literature, it may be used similarly in other disciplines. ChatGPT can facilitate the generation of most text types in various genres.
Though I am conscious of the potential pitfalls of generative AI in education, I will continue to utilise these tools and explore further how generative AI can be integrated into my classes. As tools that essentially predict statistically likely sequences of language, there is a particular relevance for linguistics students in understanding LLMs such as Chat GPT. As these tools become more sophisticated, it will be necessary to determine the stylistic patterns of LLMs as distinguishable from human-generated content. In the English Language and Literature degree, an aim is that our students will be able to investigate literary texts from a linguistic perspective to be able to describe the style of certain authors. This stylistic analysis may also be applied to artificially versus human-generated texts and will be a skill that will be increasingly sought after in the current environment of emergent generative AI technology. The construction and utilisation of LLMs in various employment contexts is an emergent prospect and graduates of language-focused courses will be at the cutting-edge of this market. As such, I am determined to expose my students to these tools, so that they are familiar with their functionality and operability.
Accompanying this below is the original opening paragraphs of George Orwell’s 1984 as well as the manipulated version of this with the text changed from the third to the first person.
George Orwell- 1984 – Original (third person)
It was a bright cold day in April, and the clocks were striking thirteen. Winston Smith, his chin nuzzled into his breast in an effort to escape the vile wind, slipped quickly through the glass doors of Victory Mansions, though not quickly enough to prevent a swirl of gritty dust from entering along with him.
The hallway smelt of boiled cabbage and old rag mats. At one end of it a coloured poster, too large for indoor display, had been tacked to the wall. It depicted simply an enormous face, more than a metre wide: the face of a man of about forty-five, with a heavy black moustache and ruggedly handsome features. Winston made for the stairs. It was no use trying the lift. Even at the best of times it was seldom working, and at present the electric current was cut off during daylight hours. It was part of the economy drive in preparation for Hate Week. The flat was seven flights up, and Winston, who was thirty-nine and had a varicose ulcer above his right ankle, went slowly, resting several times on the way. On each landing, opposite the lift-shaft, the poster with the enormous face gazed from the wall. It was one of those pictures which are so contrived that the eyes follow you about when you move. BIG BROTHER IS WATCHING YOU, the caption beneath it ran.
Inside the flat a fruity voice was reading out a list of figures which had something to do with the production of pig-iron. The voice came from an oblong metal plaque like a dulled mirror which formed part of the surface of the right-hand wall. Winston turned a switch and the voice sank somewhat, though the words were still distinguishable. The instrument (the telescreen, it was called) could be dimmed, but there was no way of shutting it off completely. He moved over to the window: a smallish, frail figure, the meagreness of his body merely emphasized by the blue overalls which were the uniform of the party. His hair was very fair, his face naturally sanguine, his skin roughened by coarse soap and blunt razor blades and the cold of the winter that had just ended.
George Orwell- 1984 – Altered (First person)
It was a bright, cold day in April, and the clocks were striking thirteen. I nuzzled my chin into my breast in an effort to escape the vile wind as I slipped quickly through the glass doors of Victory Mansions, though not quickly enough to prevent a swirl of gritty dust from entering with me.
The hallway smelled of boiled cabbage and old rag mats. At one end of it, a colored poster, too large for indoor display, had been tacked to the wall. It depicted simply an enormous face, more than a meter wide: the face of a man of about forty-five, with a heavy black mustache and ruggedly handsome features. I made for the stairs. It was no use trying the lift. Even at the best of times, it seldom worked, and at present, the electric current was cut off during daylight hours. It was part of the economy drive in preparation for Hate Week. My flat was seven flights up, and I, thirty-nine and with a varicose ulcer above my right ankle, went slowly, resting several times on the way. On each landing, opposite the lift shaft, the poster with the enormous face gazed from the wall. It was one of those pictures that are so contrived that the eyes seem to follow you about when you move. BIG BROTHER IS WATCHING YOU, the caption beneath it read.
Inside my flat, a fruity voice was reading out a list of figures that had something to do with the production of pig iron. The voice came from an oblong metal plaque like a dulled mirror, which formed part of the surface of the right-hand wall. I turned a switch, and the voice sank somewhat, though the words were still distinguishable. The instrument (the telescreen, as it was called) could be dimmed, but there was no way to shut it off completely. I moved over to the window: a smallish, frail figure, the meagerness of my body merely emphasized by the blue overalls that were the uniform of the Party. My hair was very fair, my face naturally sanguine, my skin roughened by coarse soap and blunt razor blades, and the cold of the winter that had just ended.
Reference
Orwell, George. Nineteen Eighty-Four. London: Penguin Classics, 2021. First published 1949 by Secker and Warburg (London).
- Generative AI & the Impact of Linguistic Choices on Literary Works