The Evaluating Variations in Language (EVL) Lab is an NSF funded lab that studies different applications of Stylometry e.g. Authorship Attribution, Personality Detection, Author Profiling, and Author Verification, etc.
The EVL Lab’s flagship product is JGAAP (Java Graphical Authorship Attribution Program) an open-source software project that allows non-experts to use some of the latest methods in machine learning on their text classification problems. Please visit JGAAP on GitHub.
Stylometry (also known as “authorship attribution”) is the scientific study of writing style, is an important emerging field in both computer science and humanities studies. (This specific scholastic intersection is often called “digital humanities” or DH, as typified by the NEH office of the same name.) By examining aspects of writing style such as word choice, syntax, and vocabulary, documents can be matched to their authors. Furthermore, this examination can be performed automatically, with high accuracy, by computers. EVL Labs at Duquesne University have been at the forefront of this effort for more than a decade.