Domain Adaptation for Authorship Attribution: Improved Structural Correspondence Learning

Abstract

We present the first domain adaptation model for authorship attribution to leverage unlabeled data. The model includes extensions to structural correspondence learning needed to make it appropriate for the task. For example, we propose a median-based classification instead of the standard binary classification used in previous work. Our results show that punctuation-based character n -grams form excellent pivot features. We also show how singular value decomposition plays a critical role in achieving domain adaptation, and that replacing (instead of concatenating) non-pivot features with correspondence features yields better performance.