Deep Learning and BERT-Based Models for Poetry Analysis: A Study on Chronological and Subject-Wise Categorization of Tagore’s Poetic Works

In the modern era, where artificial intelligence (AI) intersects with computational literary studies, the analysis of poetry presents both challenges and opportunities. Rabindranath Tagore’s poetry holds immense literary and historical significance, yet understanding its contextual motivations and s...

Full description

Saved in:
Bibliographic Details
Published in:SN computer science Vol. 6; no. 7; p. 904
Main Authors: Ruma, Jannatul Ferdous, Sultana, Jannat, Akter, Sharmin, Laboni, Jesrin Jahan, Rahman, Rashedur M.
Format: Journal Article
Language:English
Published: Singapore Springer Nature Singapore 15.10.2025
Springer Nature B.V
Subjects:
Accuracy
Arabic language
Arabic literature
Classification
Computer Imaging
Computer Science
Computer Systems Organization and Communication Networks
Data Structures and Information Theory
Datasets
Deep learning
Embedding
Explainable artificial intelligence
Information Systems and Communication Service
Large language models
Machine learning
Natural language processing
Original Research
Pattern Recognition and Graphics
Poetry
Poets
Semantic analysis
Semantics
Software Engineering/Programming and Operating Systems
Support vector machines
Tagore, Rabindranath (1861-1941)
Vision
Bengali poetry categorization
Deep learning
Transformer model
Explainable AI
Rabindranath tagore
Subject-based classification
Chronological classification
ISSN:2661-8907, 2662-995X, 2661-8907
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In the modern era, where artificial intelligence (AI) intersects with computational literary studies, the analysis of poetry presents both challenges and opportunities. Rabindranath Tagore’s poetry holds immense literary and historical significance, yet understanding its contextual motivations and systematically categorizing it remains complex. This study pioneers a chronological classification of Tagore’s poetry while also exploring subject-based categorization through advanced computational methods. Utilizing an AI-driven approach that integrates machine learning (ML), deep learning (DL), and natural language processing (NLP), we evaluated three ML models with two embedding methods, four DL models with four embedding methods, and five large language models (LLMs). Our methodology achieved 85.99% accuracy in subject-based classification using LSTM and BiLSTM, while chronological classification with BanglaBERT reached 75.91% accuracy. This work establishes new benchmarks in Bengali poetry analysis, demonstrating that domain-specific adaptations consistently out-perform general-purpose LLMs. Moreover, the integration of Explainable AI with LIME enhances model interpretability, bridging computational techniques with literary critique. Our findings contribute significantly to computational literary studies, offering innovative methods for exploring culturally and linguistically rich poetic contexts.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2661-8907
2662-995X
2661-8907
DOI:10.1007/s42979-025-04408-0