Mike Kestemont bio photo

Mike Kestemont

Academic researcher

Email Twitter Facebook Google+ LinkedIn Github

About

Research background

I enjoy research in computational text analysis, in particular for historic texts. Much of my work can be situated in the Digital Humanities, an international movement in which scholars from the conventional Humanities (linguistics, literary studies, history, …) explore how digital methods and computation can support and enhance traditional forms of research and teaching. Recent advances in computing technologies have, for instance, made it possible to mine cultural insights from immense text collections via “Distant Reading”. Our era thus has the historic privilege of being to able to witness and stimulate the emergence of exciting new computational research possibilities, across the Humanities at large.

Expertise

Authorship attribution is one of my main areas of expertise: in the innovative research domain of stylometry (computational stylistics), we design computational algorithms which can automatically identify the authors of anonymous texts through the quantitive analysis of individual writing styles. Computational analyses have the advantage that they induce serendipity in textual analysis: a computer makes us aware of things that the eye of the human reader tends to skip.

In my current research, I apply stylometry to medieval literature, which has often survived anonymously. A PDF of my award-winning, Dutch-language book on this topic can be freely downloaded online, a generous courtesy of my publisher, the Royal Academy for Dutch-language Linguistics and Literature. You can also check out my research in my other publications, or watch the professional online documentary in which we present some of our recent work on Hildegard of Bingen, a famous twelfth-century female mystical authoress. Together with Maciej Eder and Jan Rybicki, I have developed a free and easy to use click-and-point software package for R (Stylometry with R), which you can use to carry out stylometric analyses on your own texts.

Current

I am currently an assistant professor in the department of literature at the University of Antwerp in Belgium. In the past, I have taught various courses and workshops on Corpus and Computational Linguistics, Programming for the Humanities and medieval philology. I code in Python, tweet in English, and live in Brussels. If you are interested in collaborating, feel free to drop me a line.

Long-term

My long-term research goals involve the design and application of computational models in the context of the Humanities. Broadly speaking, the Humanities can be defined as the study of the products of the human mind. According to this definition, the task of the Humanities ultimately comes down to modeling and understanding the mind’s production processes, by reverse-engineering them. In this respect, I am particularly interested in how and why humans produce cultural artefacts, such as texts, given the constraints and opportunities of a specific historic, cultural setting. The tension between, on the one hand, individuality or creativity, and on the other hand, (limiting? stimulating?) external factors such as tradition and convention is key in my opinion.

I am an enthusiast of the Deep Learning movement in Computer Science, a promising and fast-developing research domain in which neural networks are used to mimick the human mind’s astonishing capabilities with respect to vision or language comprehension. A number of truly inspiring pieces have recently been puvlished in this field (about cats, kings and queens or music), introducing powerful techniques that simply beg to be applied in the Humanities.