Eigenmood Space: Uncertainty-Aware Spectral Graph Analysis of Psychological Patterns in Classical Persian Poetry
arXiv:2602.16959v1 Announce Type: new Abstract: Classical Persian poetry is a historically sustained archive in which affective life is expressed through metaphor, intertextual convention, and rhetorical indirection. These properties make close reading indispensable while limiting reproducible comparison at scale. We present an uncertainty-aware computational framework for poet-level psychological analysis based on large-scale automatic multi-label annotation. Each verse is associated with a set of psychological concepts, per-label confidence scores, and an abstention flag that signals insufficient evidence. We aggregate confidence-weighted evidence into a Poet $\times$ Concept matrix, interpret each poet as a probability distribution over concepts, and quantify poetic individuality as divergence from a corpus baseline using Jensen--Shannon divergence and Kullback--Leibler divergence. To capture relational structure beyond marginals, we build a confidence-weighted co-occurrence graph
arXiv:2602.16959v1 Announce Type: new Abstract: Classical Persian poetry is a historically sustained archive in which affective life is expressed through metaphor, intertextual convention, and rhetorical indirection. These properties make close reading indispensable while limiting reproducible comparison at scale. We present an uncertainty-aware computational framework for poet-level psychological analysis based on large-scale automatic multi-label annotation. Each verse is associated with a set of psychological concepts, per-label confidence scores, and an abstention flag that signals insufficient evidence. We aggregate confidence-weighted evidence into a Poet $\times$ Concept matrix, interpret each poet as a probability distribution over concepts, and quantify poetic individuality as divergence from a corpus baseline using Jensen--Shannon divergence and Kullback--Leibler divergence. To capture relational structure beyond marginals, we build a confidence-weighted co-occurrence graph over concepts and define an Eigenmood embedding through Laplacian spectral decomposition. On a corpus of 61{,}573 verses across 10 poets, 22.2\% of verses are abstained, underscoring the analytical importance of uncertainty. We further report sensitivity analysis under confidence thresholding, selection-bias diagnostics that treat abstention as a category, and a distant-to-close workflow that retrieves verse-level exemplars along Eigenmood axes. The resulting framework supports scalable, auditable digital-humanities analysis while preserving interpretive caution by propagating uncertainty from verse-level evidence to poet-level inference.
Executive Summary
This article presents a novel computational framework for analyzing psychological patterns in Classical Persian poetry. The framework utilizes uncertainty-aware spectral graph analysis, aggregating confidence-weighted evidence into a Poet × Concept matrix and quantifying poetic individuality using Jensen-Shannon divergence and Kullback-Leibler divergence. The framework is applied to a corpus of 61,573 verses across 10 poets, with 22.2% of verses abstained due to insufficient evidence. The article demonstrates a scalable and auditable digital-humanities analysis while preserving interpretive caution by propagating uncertainty from verse-level evidence to poet-level inference.
Key Points
- ▸ Uncertainty-aware computational framework for poet-level psychological analysis
- ▸ Large-scale automatic multi-label annotation of Classical Persian poetry
- ▸ Confidence-weighted co-occurrence graph over concepts and Eigenmood embedding through Laplacian spectral decomposition
Merits
Innovative Methodology
The article introduces a novel framework that combines machine learning and spectral graph analysis to analyze psychological patterns in poetry, providing a new perspective on literary analysis.
Scalability and Audibility
The framework is designed to be scalable and auditable, allowing for the analysis of large corpora of text while maintaining transparency and accountability in the analytical process.
Demerits
Limited Generalizability
The framework is specifically designed for analyzing Classical Persian poetry, which may limit its generalizability to other literary genres or languages.
Abstention Rate
The high abstention rate of 22.2% may indicate that the framework requires further refinement to improve its accuracy and reduce uncertainty in the analysis.
Expert Commentary
This article presents a significant contribution to the field of digital humanities, demonstrating the potential of computational methods to analyze and interpret literary texts. The framework's ability to propagate uncertainty from verse-level evidence to poet-level inference is a particularly notable feature, as it allows for a more nuanced and cautious approach to analysis. However, further research is needed to refine the framework and improve its generalizability to other literary genres and languages. Additionally, the article's emphasis on transparency and accountability in the analytical process has important implications for the development of policies and guidelines for digital humanities research.
Recommendations
- ✓ Future research should focus on refining the framework to improve its accuracy and reduce uncertainty in the analysis.
- ✓ The framework should be applied to other literary genres or languages to test its generalizability and provide new insights into psychological patterns and themes present in different types of texts.
