I’m a Lecturer at Tilburg University, as well as a joint PhD candidate doing research for both the CS&AI group at Tilburg and CLiPS at the University of Antwerp under the supervision of Eric Postma, Grzegorz Chrupała, and Walter Daelemans. I currently teach Text Mining and Social Data Mining in context of the new Data Science master. Before, I worked for the AMiCA project where my research was mainly in the field of Text Mining. During this, I focussed on applying Machine Learning for forensic and online security-related applications such as detection of cyberbullying and child grooming, and author profiling. On top of this, I developed software to apply these techniques on social media.
After obtaining a BA in Communication and Information Sciences from Tilburg University, I realized soon enough that Artificial Intelligence and programming were very much my thing. Hence, I stayed in Tilburg and obtained an MSc in Human Aspects of Information Technology cum laude. I wrote quite the pile of pages that made my master thesis under the supervision of Menno van Zaanen on discovering trends in societal debates by means of Supervised Topic Modelling on online news sources, for which I had the honour of receiving two awards (Leo Coolen & STIL). With my newly developed admiration for Natural Language Processing and Machine Learning, I sought to continue research and applied (and got hired) for a PhD position in Antwerp. After two years of dilligent work, I was offered to continue my work and lecture at Tilburg University, where I reside today.
During my studies I learned to speak most notably Python, PHP, and Java, became an avid Linux user and got very enthusiastic about open-source software, and thus open data and open science initiatives. I started a sole proprietorship in web development and data collection, and scripting was a large part of my student assistantship activites. All in all, I typed a whole bunch of code for websites, wrappers, and tools. My latest endeavors include a minimalistic conference manager (ebacs), a Python wrapper for Stanford’s Topic Modelling Toolbox (topbox), and an environment for Text Mining research (Omesa). More details can be found here.