Assessing the ability of generative AI in English literary analysis through Bloom’s Taxonomy

This study delves into the capabilities of generative artificial intelligence (GenAI) in performing literary analysis across various genres in the English language, including novels and plays. Based on the framework of Bloom’s Taxonomy, which categorises learning objectives into six hierarchical levels – remembering, understanding, applying, analysing, evaluating, and creating, this research aimed to shed light on the depth and breadth of ChatGPT-4’s analytical capabilities in literature. Through a systematic and iterative process, this study employed a set of rubrics tailored to each cognitive level of Bloom’s to assess ChatGPT-4’s responses to three literary texts with different genres, settings, and themes. The evaluation, conducted by a panel of four university teachers with a background in education and English in Hong Kong, focused on three critical criteria: the depth, accuracy, and relevance of the AI’s responses. This was followed by individual semi-structured interviews with the participants. The results underscore the potential of AI to enhance literary studies. The implications for curriculum development and pedagogical strategies in higher education are discussed, advocating for a structured integration of AI to enhance learning experiences while addressing the inherent limitations of AI in capturing the subtleties of humanistic inquiry. This research contributes to the growing discourse on AI in education, offering insights into the utility and limitations of GenAI tools in fostering deep engagement with literature and the development of critical analytical skills.