Stylometry System - Use Cases and Feasibility Study

Stylometry is a discipline that determines authorship of literary works through the use of statistical analysis and machine learning. While this discipline has been used successfully to determine authorship of famous literary works, the area of analyzing digital content is still relatively new with much more to discover. Since the early to mid 1990’s the explosion of the Internet has opened up new uses for stylometry in the area of email, social networking, and various types of digital content. This paper is divided into two parts. Part I discusses potential uses of stylometry in the area of Internet content and presents four use cases in areas that have had little or no research. Part II evaluates three existing stylometry tools and conducts a feasibility study to determine if the tools can correctly assign authorship of electronic mail to its original author.