Studying Linguistic Changes over 200 Years of Newspapers through Resilient Words Analysis

Abstract

This paper presents a methodology to analyze linguistic changes in a given textual corpus allowing to overcome two common problems related to corpus linguistics studies. One of these issues is the monotonic increase of the corpus size with time, and the other one is the presence of noise in the textual data. In addition, our method allows to better target the linguistic evolution of the corpus, instead of other aspects like noise fluctuation or topics evolution. A corpus formed by two newspapers "La Gazette de Lausanne" and "Le Journal de Genève" is used, providing 4 million articles from 200 years of archives. We first perform some classical measurements on this corpus in order to provide indicators and visualizations of linguistic evolution. We then define the concept of a lexical kernel and word resilience, to face the two challenges of noises and corpus size fluctuations. This paper ends with a discussion based on the comparison of results from linguistic change analysis and concludes with possible future works continuing in that direction.

Corpus linguistics, newspaper archives and historical research methods

“…While much of the existing corpora are in the English language, similar efforts can be pursued by researchers to push for newspaper digitisation and access to research. For example, Buntinx et al (2017) have conducted linguistic analysis of two French newspapers that contain four million articles and two billion words over two hundred years. As this method grows in popularity, it is likely that the number of research tools will expand as researchers ask for more customised solutions.…”

“…Their work approached the matter separately from the historian’s and linguists perspective and then in combination, to generate new insights and hypotheses. While their corpora include books and texts, linguists have also begun exploring the potential of unravelling patterns in linguistic evolution using digitised newspaper databases (Westin and Geisler, 2002; Fries and Lehmann, 2006; Bamford et al , 2013; Buntinx et al , 2017).…”