News Authorship Identification with Deep Learning

Authorship identification identifies the most possible author from a group of candidate authors for academic articles, news, emails and forum messages. It can be applied to find the original author of an uncited article, to detect plagiarism and to classify spam / nonspam messages. In this project, we tackled this classification task in author level, article level, sentence level and word level with various deep and non-deep classification algorithms and GloVe word vectors are used as the pre-trained word vectors. Among all the algorithms, sentence-level Recurrent Neural Network (RNN) achieves the best performance since it captures the context information as well as word / sentence sequence information from the training dataset.