It's all frequency? - testing usage-based theories of language change using agent-based models

This project proposes to use regularization methods from machine learning, more specifically Elastic Net regression (and its siblings Ridge and Lasso), to look into lexical semantic effects in morphosyntactic alternances. These regularization techniques apply shrinkage to the coefficients and can thus be used for variable selection, especially when the number of predictors is very large. In variationist studies, this is often the case if one wishes to enter lexemes associated with a construction into a regression model to predict constructional variants. We combine the Elastic Net regulator with k-fold cross-validation - a standard procedure - to avoid overfitting. Our approach mitigates the various drawbacks present in alternative approaches that are currently used in variationist linguistics, like random factors in mixed models and collostructional analysis. We look at ten multifactorially driven alternances from Dutch. The project offers a transparent pipeline that can easily be extrapolated to other case studies, and to other languages.