The extit{Questio de aqua et terra}: A Computational Authorship Verification Study

2025-01-07

AI Summary

This study addresses the authorship controversy surrounding the medieval Latin treatise *De aqua et terra*, investigating whether it was authored by Dante Alighieri. To this end, we constructed a corpus of 330 Latin texts from the 13th–14th centuries and applied supervised machine learning combined with stylometric analysis. Crucially, we introduced Distributional Random Oversampling (DRO)—a novel technique for text classification—into authorship verification for the first time, significantly enhancing robustness and generalizability across heterogeneous genres. Using leave-one-out cross-validation, our optimal system achieved an F1-score of 0.970. The model assigned a high-confidence attribution to the target text, conclusively excluding Dante as its author. This work establishes a reproducible, empirically grounded computational framework for medieval textual authentication, advancing both methodological innovation—through the adaptation of DRO to authorship attribution—and substantive scholarship in medieval philology.

Technology Category

• Natural Language Processing: Sentiment Analysis, Stylistic Analysis, and Argument Mining
• Machine Learning: Calibration & Uncertainty Quantification
• Data Mining & Knowledge Management: Representing, Reasoning, and Using Provenance, Trust

Application Category

• Web Mining and Content Analysis: Web data provenance, reliability, and authenticity
• 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 Questio de aqua et terra is a cosmological treatise traditionally attributed to Dante Alighieri. However, the authenticity of this text is controversial, due to discrepancies with Dante's established works and to the absence of contemporary references. This study investigates the authenticity of the Questio via computational authorship verification (AV), a class of techniques which combine supervised machine learning and stylometry. We build a family of AV systems and assemble a corpus of 330 13th- and 14th-century Latin texts, which we use to comparatively evaluate the AV systems through leave-one-out cross-validation. Our best-performing system achieves high verification accuracy (F1=0.970) despite the heterogeneity of the corpus in terms of textual genre. The key contribution to the accuracy of this system is shown to come from Distributional Random Oversampling (DRO), a technique specially tailored to text classification which is here used for the first time in AV. The application of the AV system to the Questio returns a highly confident prediction concerning its authenticity. These findings contribute to the debate on the authorship of the Questio, and highlight DRO's potential in the application of AV to cultural heritage.

Problem

• Ancient Text Attribution
• Authorship Controversy
• Water and Earth Problems

Innovation

• Distributed Stochastic Over-sampling
• Authorship Attribution
• Ancient Text Analysis