Wallace: Author Detection via Recurrent Neural Networks

Author detection or author attribution is an important field in NLP that enables us to verify the authorship of papers or novels and allows us to identify anonymous authors. In our approach to this classic problem, we attempt to classify a broad set of literary works by a large number of distinct authors using traditional and deep-learning techniques, including Multinomial Naive Bayes, linear SVMs, and Recurrent Neural Networks (RNN).