Incorporating Artificial Intelligence (AI) into the education sector is evidence of a shift towards innovative assessment methods. This study focuses on the application of ChatGPT in assessing English literature essays written by undergraduate students, specifically by second-year students enrolled in the Teaching English Language and Literature programme. With AI technologies, particularly ChatGPT, gaining prominence for their role in educational advancements, this research explores the utility of ChatGPT 4o in streamlining assessment processes such as grading and providing feedback.

This paper employs a comparative analysis to investigate the effectiveness of ChatGPT in grading approximately ten student essays, comparing the AI-driven assessments with those carried out by human assessors. The focus is on exploring ChatGPT's ability to provide personalised feedback, a feature that contrasts with traditional assessment methods. Using qualitative assessment metrics, the study evaluates the precision, responsiveness and depth of feedback provided by ChatGPT to determine the extent to which AI can match or outperform human assessors in understanding and assessing the complex textual analysis inherent in English literature essays.

The findings suggest that ChatGPT has significant potential to revolutionise the assessment landscape by providing immediate, tailored feedback, potentially enhancing the educational experience. However, the research also highlights critical challenges, such as ensuring a nuanced understanding of literary analysis and addressing ethical concerns associated with automated assessment systems.

By providing insights into the comparative effectiveness of ChatGPT and human assessment, this research contributes to the ongoing dialogue on the integration of AI tools in education and advocates for their strategic implementation to improve pedagogical practices and student learning outcomes in the field of English literature.

Keywords: AI, ChatGPT4o, assessment, English Literature, essay.