Between Century and Poet: Graph-Based Lexical Semantic Change in Persian Poetry

2026-04-08

AI Summary

This study investigates the historical evolution of lexical semantics in Persian poetry while disentangling the effects of diachronic change from individual poetic style. To this end, the authors propose a modeling framework based on semantic neighborhood reconfiguration: by aligning Word2Vec embeddings across time periods, they construct a diachronic semantic graph and apply graph-theoretic analysis, community detection, and lexical auditing to trace the dynamic relational networks of twenty target words and five anchor terms across centuries of poetic corpora. The findings reveal that semantic change manifests primarily through structural reconfigurations—such as gains and losses of semantic neighbors, shifts in bridging roles, and community migrations—rather than mere vector drift. This approach better captures the persistence and selective transformation of meaning in literary contexts, offering digital humanities a more interpretable computational paradigm.

Abstract

Meaning in Persian poetry is both historical and relational. Words persist through literary tradition while shifting their force through changing constellations of neighbors, rhetorical frames, and poetic voices. This study examines that process using aligned Word2Vec spaces combined with graph-based neighborhood analysis across centuries and major poets. Rather than modeling semantic change as vector displacement alone, it treats lexical history as the rewiring of local semantic graphs: the gain and loss of neighbors, shifts in bridge roles, and movement across communities. The analysis centers on twenty target words, anchored by five recurrent reference terms: Earth, Night, two wine terms, and Heart. Surrounding them are affective, courtly, elemental, and Sufi concepts such as Love, Sorrow, Dervish, King, Annihilation, and Truth. These words exhibit distinct patterns of change. Night is more time-sensitive, Earth more poet-sensitive, and Heart shows continuity despite graph-role mobility. The two wine terms highlight probe sensitivity: one is broad and semantically diffuse, while the other is narrower and more stable. A lexical audit confirms that the corpus contains historically driven terms, poet-specific usages, and sparsely attested mystical vocabulary requiring caution. Overall, semantic change in Persian poetry is better captured as neighborhood rewiring than as abstract drift. For Digital Humanities, this approach restores local structure to computational analysis and supports interpretations closer to literary practice: persistence, migration, mediation, and selective transformation.

Problem

• semantic change
• Persian poetry
• lexical semantics
• graph-based analysis
• historical linguistics

Innovation

• graph-based semantic change
• aligned Word2Vec
• neighborhood rewiring
• lexical history
• Digital Humanities