Modeling the dynamics of language change: logistic regression, Piotrowski's law, and a handful of examples in Polish

TL;DR

This paper applies logistic regression to model historical language changes in Polish from the 15th to 18th centuries, extending Piotrowski's law with polynomial models and analyzing multiple change cases jointly.

Contribution

It introduces polynomial logistic regression for language change modeling and evaluates the influence of corpus size on model accuracy.

Findings

Most language changes follow expected nonlinear patterns

Polynomial logistic regression improves model fit for complex changes

Subcorpus size affects the goodness-of-fit of the models

Abstract

The study discusses modeling diachronic processes by logistic regression. The phenomenon of nonlinear changes in language was first observed by Raimund Piotrowski (hence labelled as Piotrowski's law), even if actual linguistic evidence usually speaks against using the notion of a "law" in this context. In our study, we apply logistic regression models to 9 changes which occurred between 15th and 18th century in the Polish language. The attested course of the majority of these changes closely follow the expected values, which proves that the language change might indeed resemble a nonlinear phase change scenario. We also extend the original Piotrowski's approach by proposing polynomial logistic regression for these cases which can hardly be described by its standard version. Also, we propose to consider individual language change cases jointly, in order to inspect their possible collinearity or, more likely, their different dynamics in the function of time. Last but not least, we evaluate our results by testing the influence of the subcorpus size on the model's goodness-of-fit.