Artificial Intelligence for Sentiment Analysis of Persian Poetry

2026-03-11

AI Summary

This study investigates whether modern large language models can accurately interpret sentiment in classical Persian poetry and its interplay with poetic meter. We present the first systematic evaluation of BERT and GPT-family models—including GPT-4o—on joint sentiment–prosody analysis of poems by Rumi and Parvin E’tesami, leveraging natural language processing to mitigate subjective biases inherent in manual interpretation. Our findings indicate that GPT-4o reliably discerns poetic sentiment, with Rumi’s corpus exhibiting a more positive overall affect and significantly greater expressive diversity through metrical variation compared to E’tesami’s work. This research establishes a novel computational paradigm for cross-cultural poetic analysis, demonstrating the potential of advanced language models to uncover nuanced emotional and structural patterns in non-Western literary traditions.

Technology Category

• Natural Language Processing: Sentiment Analysis, Stylistic Analysis, and Argument Mining
• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Computational Creativity

Application Category

• Web Mining and Content Analysis: Sentiment analysis and opinion mining
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success

Abstract

Recent advancements of the Artificial Intelligence (AI) have led to the development of large language models (LLMs) that are capable of understanding, analysing, and creating textual data. These language models open a significant opportunity in analyzing the literature and more specifically poetry. In the present work, we employ multiple Bidirectional encoder representations from transformers (BERT) and Generative Pre-trained Transformer (GPT) based language models to analyze the works of two prominent Persian poets: Jalal al-Din Muhammad Rumi (Rumi) and Parvin E'tesami. The main objective of this research is to investigate the capability of the modern language models in grasping complexities of the Persian poetry and explore potential correlations between the poems' sentiment and their meters. Our findings in this study indicates that GPT4o language model can reliably be used in analysis of Persian poetry. Furthermore, the results of our sentiment analysis revealed that in general, Rumi's poems express happier sentiments compared to Parvin E'tesami's poems. Furthermore, comparing the utilization of poetic meters highlighted Rumi's poems superiority in using meters to express a wider variety of sentiments. These findings are significant as they confirm that LLMs can be effectively applied in conducting computer-based semantic studies, where human interpretations are not required, and thereby significantly reducing potential biases in the analysis.

Problem

• Sentiment Analysis
• Persian Poetry
• Language Models
• Poetic Meters
• Artificial Intelligence

Innovation

• Large Language Models
• Sentiment Analysis
• Persian Poetry
• Poetic Meter
• GPT-4o