Welcome!
I am a PhD student at Carnegie Mellon University (CMU), School of Computer Science, Computation, Organization, Society (COS) program, CASOS lab, advised by Kathleen M. Carley.
My mission is to span a boundary between computational linguistics (aka natural language processing) and relational data analysis (aka network analysis) (some details on my work). I started working on this idea in order to better understand the co-evolution and interplay of the semantics and mechanics of real-world networks. More precisely, I am concerned with the informed and efficient extraction of relevant (that is, user-defined) instances of node and edge classes from unstructured, natural language text data. CMU is a great environment for doing this.
After working towards this goal from a computational and empirical standpoint for a couple of years we began to realize that there is another dimension to it: The challenge here is not just the interdisciplinary research, publications or projects that we can engage in, but it's yet again about the people - we need to build bridges between people who develop computational solutions and the consumers of those tools, techniques, measures, etc.. This involves computational communication; an idea related to Jeanette Wing's call for computational thinking.
Why? Because probabilistic techniques that we work with only approximate network structures from texts, and because modern algorithms and techniques are complex in their underlying theories, models, algorithms and parameters. As a result, solutions handed over to end-users carry along certain decisions, some of which the user should know about. In order to address this challenge we currently investigate the sensitivity (kind of reverse engineering of robustness analysis) of supervised and semi-supervised sequential stochastic machine learning techniques with respect to the impact of computational decisions on relational data that is distilled from texts. I welcome any thoughts, feedback, critiques etc. on that on that I would be glad to hear from you.
Relational data and computational linguistics: My ongoing interest is the automated extraction of relational data from texts. This has led me to research on algorithms for relation extraction (some of which are available in a toolkit that we built at CMU (AutoMap) as well as to the application of these techniques to a variety of questions and domains.
Networks: I study real-world (that is, dynamic, complex, large) socio-technical, especially such that face a change or emergency. In that context, our empirical work has been focusing on business organizations (e.g. Enron), governmental organizations (e.g. FEMA), and covert networks.