A Statistical Exploration of Text Partition Into Constituents: The Case of the Priestly Source in the Books of Genesis and Exodus

TL;DR

This paper introduces a statistical pipeline for analyzing text partitions, validated on biblical texts to distinguish stylistic differences between Priestly and non-Priestly components using stylometry and hypothesis testing.

Contribution

The paper presents a novel pipeline combining stylometry, hypothesis testing, and feature importance analysis for text partition validation, applied to biblical texts.

Findings

Significant stylistic differences identified between Priestly and non-Priestly texts.

Pipeline effectively quantifies and validates text partition hypotheses.

Method reveals key stylistic features distinguishing text components.

Abstract

We present a pipeline for a statistical textual exploration, offering a stylometry-based explanation and statistical validation of a hypothesized partition of a text. Given a parameterization of the text, our pipeline: (1) detects literary features yielding the optimal overlap between the hypothesized and unsupervised partitions, (2) performs a hypothesis-testing analysis to quantify the statistical significance of the optimal overlap, while conserving implicit correlations between units of text that are more likely to be grouped, and (3) extracts and quantifies the importance of features most responsible for the classification, estimates their statistical stability and cluster-wise abundance. We apply our pipeline to the first two books in the Bible, where one stylistic component stands out in the eyes of biblical scholars, namely, the Priestly component. We identify and explore statistically significant stylistic differences between the Priestly and non-Priestly components.