Welcome!
I am a fourth year PhD student at Carnegie Mellon University (CMU), School of Computer Science, Center for Computational Analysis of Social and Organizational Systems (CASOS), in the Computation, Organizations and Society (COS) program. My advisor is Kathleen Carley.
In my research I aim to span the boundary between computational linguistics and natural language processing (NLP) on one side and relational data analysis (also known as network analysis) on the other side (some details). This work is driven by my search for a better understanding of the co-evolution and interplay of the semantics and mechanics of real-world networks.
CMU and the CASOS lab have been a great environment for doing this kind of interdisciplinary computational work:
I started out by being a developer for AutoMap, an NLP and relational text analysis package now supported by a team of CASOS folks. For this endeavor, my previously acquired degree in communication science turned out to be helpful. From a technical and methodological perspective, I am concerned with the informed, accurate and efficient extraction of relevant instances of node and edge classes from unstructured, natural language text data. I am working on various machine learning and artificial intelligence techniques for this purpose. This has led me to the development of new techniques for network analysis of texts and the application of these techniques to various problems and domains. Furthermore, I have been testing the sensitivity of information and relation extraction results and network analytical measures to these various techniques.
From a theoretical and empirical and perspective, I am interested in the computational integration of semantic analyses and real-world networks. I have been applying this approach to study various dynamic and complex socio-technical systems, such as small teams of collaborators, some larger social groups (e.g. Sudan), the Enron corporation, and various covert networks. Much of this work is embedded in team efforts in our lab, for instance a recent project on culture and narratives in virtual worlds.
Some details on AutoMap: the tool supports users in distilling relational data (more specifically, mental models of individuals and groups as well as the structure of social and organizational systems) from texts as well as a wide range of NLP and information extraction routines, such as such the identification of central terms and themes in across single or multiple documents, positive and negative filters, stemming (translating words into their morphemes), parts of speech tagging (assign part of speech to every word), anaphora resolution (translate pronouns into the social entities that the pronoun refers to), named entity extraction (identification of agents, organizations and places that are referred to by a name), and text coding according to user-defined ontologies. As a by-product, AutoMap supports classical Content Analysis.