AETAS: Analysis of Evolving Temporal Affect and Semantics for Legal History

TL;DR

This paper introduces a reproducible pipeline for analyzing lexical and semantic shifts over time in legal texts, providing interpretable insights into historical legal language and concepts.

Contribution

It presents a novel, interpretable, and reproducible method for quantifying lexical drift and semantic change in historical legal corpora, coupling visualization with legal relevance.

Findings

Legal language evolves with penal reforms and moral debates.

Semantic trajectories reveal shifts in concepts like justice and insanity.

The pipeline is adaptable to other historical texts.

Abstract

Digital-humanities work on semantic shift often alternates between handcrafted close readings and opaque embedding machinery. We present a reproducible expert-system style pipeline that quantifies lexical drift and its instability in the Old Bailey Corpus (1674-1913), coupling interpretable trajectories with legally meaningful axes. We bin proceedings by decade with dynamic merging for low-resource slices, train skip-gram embeddings, align spaces through orthogonal Procrustes to a 1900s anchor, and measure both geometric displacement and neighborhood turnover. We add split-half baselines and seed-sensitivity checks to separate within-bin instability from temporal change. Three visual analytics outputs (drift magnitudes, semantic trajectories, and movement along a mercy-versus-retribution axis) expose how justice, crime, poverty, and insanity evolve with penal reforms, transportation debates, and Victorian moral politics. The pipeline is implemented as auditable scripts so results can be reproduced in other historical corpora.