The problem of identifying the author of a particular text has been around for centuries. The relative anonymity that the written word or digitally printed character can provide has meant that those wishing to take on the role of investigator have had to resort to a number of unique, often cutting-edge methods to identify the person behind a particular piece of text.
With the proliferation of machine learning, deep learning, and data science in general, the potential for authorship analysis is higher now than it ever has been, and the ability for researchers to extract more information from smaller text sets has improved dramatically. This is of particular value for academics, investigators, and members of law enforcement interested in identifying the authorship of anonymous online texts from suspects or known criminals.
My research in turn is focused on the development of techniques and tools to conduct authorship analysis of users on the dark web. This will ideally culminate in the development of a platform for investigators to conduct authorship analysis on the dark web without needing to construct their own authorship analysis models. Moreover, my work is also focused on designing methods that improve the performance of authorship analysis models, and increase the level of confidence that investigators can place in the results the models provide.
I am a member of the following research groups: