HistLens: Mapping Idea Change across Concepts and Corpora

TL;DR

HistLens is a novel framework that tracks and compares the semantic evolution of multiple concepts across different corpora over time, enhancing diachronic analysis in social sciences and humanities.

Contribution

It introduces a unified SAE-based approach for multi-concept, multi-corpus analysis, enabling interpretable and comparable trajectories of idea change.

Findings

Supports cross-concept and cross-corpus analysis of idea evolution.

Enables implicit concept computation from long-span press corpora.

Provides a shared coordinate system for conceptual trajectories.

Abstract

Language change both reflects and shapes social processes, and the semantic evolution of foundational concepts provides a measurable trace of historical and social transformation. Despite recent advances in diachronic semantics and discourse analysis, existing computational approaches often (i) concentrate on a single concept or a single corpus, making findings difficult to compare across heterogeneous sources, and (ii) remain confined to surface lexical evidence, offering insufficient computational and interpretive granularity when concepts are expressed implicitly. We propose HistLens, a unified, SAE-based framework for multi-concept, multi-corpus conceptual-history analysis. The framework decomposes concept representations into interpretable features and tracks their activation dynamics over time and across sources, yielding comparable conceptual trajectories within a shared coordinate system. Experiments on long-span press corpora show that HistLens supports cross-concept, cross-corpus computation of patterns of idea evolution and enables implicit concept computation. By bridging conceptual modeling with interpretive needs, HistLens broadens the analytical perspectives and methodological repertoire available to social science and the humanities for diachronic text analysis.