用统一框架分析多个概念在不同语料中的思想演变，突破传统研究局限。
HistLens: Mapping Idea Change across Concepts and Corpora
- 基于SAE的统一框架，分解概念表征为可解释特征。
- 跨概念跨语料追踪概念激活动态，实现可比性轨迹分析。
- 支持隐含概念计算，适合历史社会学与人文社科研究者。
语言变化既反映也塑造社会进程，基础概念的语义演化为历史与社会变迁提供了可测量的痕迹。尽管近期在历时语义与话语分析方面取得进展，现有计算方法通常（一）仅聚焦单一概念或单一语料，导致跨异质来源的结果难以比较；（二）局限于表面词汇证据，当概念以隐含方式表达时，缺乏足够的计算与解释粒度。本文提出HistLens，一种基于SAE的统一框架，用于多概念、多语料的概念史分析。该框架将概念表征分解为可解释特征，并追踪其在时间和跨来源中的激活动态，生成共享坐标系下的可比概念轨迹。在长跨度新闻语料上的实验表明，HistLens支持跨概念、跨语料的思想演化模式计算，并能实现隐含概念的推断。通过连接概念建模与解释需求，HistLens拓展了社会科学与人文学科进行历时文本分析的视角与方法工具箱。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。