A Bolu: A Structured Dataset for the Computational Analysis of Sardinian Improvisational Poetry

2026-04-21

AI Summary

This study addresses the longstanding absence of structured corpora for improvised poetry in the Logudorese variety of Sardinian, a gap that has hindered both computational linguistic analysis and the preservation of oral traditions. The authors present A Bolu, the first structured corpus of this poetic form, comprising 2,835 stanzas and 141,321 tokens. Through descriptive statistics and computational linguistic methods, they conduct a multidimensional textual analysis and provide the first empirical evidence of significant formulaic repetition patterns in this oral poetry. These findings offer robust support for the Parry-Lord theory of oral-formulaic composition while advancing inclusive development of NLP resources for minority languages and opening new avenues for understanding oral creativity.

Technology Category

• Natural Language Processing: Sentiment Analysis, Stylistic Analysis, and Argument Mining
• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Application Domains: Humanities & Computational Social Science

Application Category

• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

The growing interest of Natural Language Processing (NLP) in minority languages has not yet bridged the gap in the preservation of oral linguistic heritage. In particular, extemporaneous poetry - a performative genre based on real-time improvisation, metrical-rhetorical competence - remains a largely unexplored area of computational linguistics. This methodological gap necessitates the creation of specific resources to document and analyse the structures of improvised poetry. This is the context in which A Bolu was created, the first structured corpus of extemporaneous poetry dedicated to cantada logudorese, a variant of the Sardinian language. The dataset comprises 2,835 stanzas for a total of 141,321 tokens. The study presents the architecture of the corpus and applies a multidimensional analysis combining descriptive statistical indices and computational linguistics techniques to map the characteristics of the poetic text. The results indicate that the production of Sardinian extemporaneous poets is characterised by recurring patterns that support Parry and Lord's theory of formulaicity. This evidence not only provides a new key to understanding oral creativity, but also offers a significant contribution to the development of NLP tools that are more inclusive and sensitive to the specificities of less widely spoken languages.

Problem

• extemporaneous poetry
• Sardinian language
• oral linguistic heritage
• computational linguistics
• minority languages

Innovation

• extemporaneous poetry
• structured corpus
• Sardinian language
• formulaicity
• computational linguistics