Author verification: basic stacked generalization applied to predictions from a set of heterogeneous learners

Abstract

In this paper we present the system we submitted to the PAN 2015 competition for the author verification task. We consider the task as a supervised classification problem, where each case in a dataset is an instance. Our approach combines the output from multiple learners using basic stacked generalization. The individual learners are obtained using five distinct approaches, each trained using a generic genetic algorithm. Our system performed well on the test set: the macro-average score was 0.61 (2nd best).