CS578_ML_project
#Introduction
Author identification is an application on natural language processing, which is concerned with the classification of a document by author. In other words, given a documents and a list of authors, our objective is to match the document with its corresponding author. One other variant of this task is predicting the authors' attributes such as gender, demographics, age etc. Our work here can be easily extended to answer some of these variants.\
Many applications can make use of a working author identification tool as: \begin{itemize} \item It may help label numerous online unlabeled documents by author. \item It may be very useful to detect authors for double/triple blind submission conferences. Many conferences stick to "one paper per author" policy and this may help to maintain that. \item It may be used in identifying fraud pieces of news claimed to be written by someone. \item It may help with detecting plagiarism. \item Other variants as author gender identification can be useful for statistical analysis and social sciences. \end{itemize}