Unveiling Temporal Trends in 19th Century Literature: An Information Retrieval Approach

TL;DR

This paper investigates how term usage and thematic concepts evolve across 19th-century English fiction using an information retrieval framework. By segmenting a large British Library corpus (BL19) into decades and applying a relevance-based query expansion approach, the authors quantify linguistic and conceptual shifts with metrics including Kendall's $\tau$, Jaccard similarity, and Jensen-Shannon divergence to compare decade-specific expansions against the full collection. Key findings reveal substantial divergence in expansion terms across decades, reflecting dynamic semantic spaces, with concrete observations such as variable overlaps for certain terms and relatively stable overall divergence values around $0.5$ across decade pairs. The proposed approach provides a reproducible lens for humanities researchers to explore diachronic language change in historical corpora and suggests future extensions to non-fiction texts and interactive visualization tools for semantic trend exploration.

Abstract

In English literature, the 19th century witnessed a significant transition in styles, themes, and genres. Consequently, the novels from this period display remarkable diversity. This paper explores these variations by examining the evolution of term usage in 19th century English novels through the lens of information retrieval. By applying a query expansion-based approach to a decade-segmented collection of fiction from the British Library, we examine how related terms vary over time. Our analysis employs multiple standard metrics including Kendall's tau, Jaccard similarity, and Jensen-Shannon divergence to assess overlaps and shifts in expanded query term sets. Our results indicate a significant degree of divergence in the related terms across decades as selected by the query expansion technique, suggesting substantial linguistic and conceptual changes throughout the 19th century novels.