An AI-Driven Framework for Computational Literary Analysis: Bridging English Literature and Technology

Title

An AI-Driven Framework for Computational Literary Analysis: Bridging English Literature and Technology

Creator

Jiby Jose, E.; Biswas, Priyanka

Description

Artificial Intelligence is emerging to be significantly used in the field of digital humanities, yet the focus of achieving interpretability and predictive level of performance simultaneously in the field of literary analysis is challenging. This paper highlights the study of a newly proposed effective model that is the Interpretable and Pedagogical Artificial Intelligence Framework (IPAF), a novel model that is designed for the analysis of poetry, prose and drama, while suitable outputs are provided by the model that are explainable in the field of education and literature research. The traditional models, such as the Random Forest, XG Boost and the Light BGM model, were used as base learners and have been integrated into the IPAF model by using Term Frequency-Inverse Document Frequency (TF-IDF) and the BERT embedding towards feature-level representations. The evaluation of this framework is carried out by utilising standard levels of classification metrics such as precision, accuracy level, F1 score and the SHAP-based explainability, which is applied for identifying the significant features of text that are influencing predictions. The results show that the IPAF model significantly outperforms the existing baseline models, by achieving a model with high accuracy, stability and robustness, that provides actionable insights towards educators and literary researchers. The interpretability of the framework allows users towards linking the computational outputs of the model alongside stylistic and theme-based patterns, by bridging the need for qualitative analysis along critical understanding of the literature. The future scope of the work extends the IPAF model to explore multi-modal levels of literary analysis by integrating data for audio, text and image together for digital archives for the further enhancement of cross-genre interpretation and applications of pedagogy. 2025 IEEE.

Source

2025 IEEE 5th International Conference on ICT in Business Industry and Government, ICTBIG 2025;

Date

01-01-2025

Publisher

Institute of Electrical and Electronics Engineers Inc.

Subject

AI-Driven Literary Analysis; Interpretable and Pedagogical Artificial Intelligence Framework (IPAF); LightGBM; Multi-modal Literary Analysis; Random Forest; XGBoost

Coverage

Jiby Jose E., CHRIST (Deemed to Be University), Bangalore, India; Biswas P., CHRIST (Deemed to Be University), Bangalore, India

Rights

Restricted Access; Hardcopy may be available in the library

Relation

ISBN: 979-833157981-4;

Format

online

Language

English

Type

Conference paper

Identifier

https://doi.org/10.1109/ICTBIG68706.2025.11323856

https://www.scopus.com/pages/publications/105032843598?origin=resultslist