Dr. George Mikros of National and Kapodistrian University of Athens and the University of Massachusetts, Boston is presenting a workshop for us:
The aim of this workshop is to provide a hands-on training on analyzing textual collections using computational methods and tools and exploring stylistic variation and authorship research questions. In the recent years computational stylistics methods have been evolved considerably incorporating state of the art methods of machine learning and natural language processing. We will present both the recent developments in the field and provide practical training on real research questions arising from the digital humanities scholarship.
The workshop will be structured in two parts. The first will be a theoretical introduction to the basic concepts behind stylometry, including the basic linguistic premises (idiolect theory) and the most important stylometric linguistic features used (i.e. most frequent words, character and word n-grams etc.). The second part will focus on hands-on experience on analyzing corpora using computational stylistic tools and methods. We will present the package “Stylo”, a library for stylometric analysis that is based on the R programming language. Stylo offers a friendly GUI which can be used even by students with no particular training on R or any other programming language environment. Using “Stylo” we will analyze a corpus of English novels of the 19th century and we will solve a literary mystery detecting the real author of a book of unknown authorship!
Comments