Who wrote this paper? Learning for authorship de-identification using stylometric featuress

In this paper, we propose to combine stylometric features and neural networks for authorship de-identification. Our research mainly focuses on scientific publications, because scholarly journals are publicly available with plenty of labeled data to learn an author´s style or traits. The main challenge of authorship de-identification is to identify features which can properly capture an author´s writing style. In the proposed design, we choose a combination of stylometric features, including lexical, syntactic, structural and content-specific features, to represent each author´s style and use them to build classification models. We manually collect publications from computer science and biomedicine domains and validate our designs by using a number of classification methods. Our experiments show that among four well-known classifiers, Multilayer Perceptron (MLP) classifiers achieve the best performance for authorship de-identification.