Research Interests
My research deals with the analysis of spontaneous language samples. I work with written language mostly, but some of my work also deals with transcriptions of spoken language. My main research projects can be categorized along these lines:

  • Forensic linguistics, including authorship attribution, profiling and plagiarism detection
  • Computational Linguistics for the analysis of Code-Switched data
  • Health informatics (information extraction from patient generated data)
  • Clinical NLP, the use of NLP in language assessment for a clinical purpose (diagnose, monitor conditions affecting language patterns)

Research Group
I’m the founder and director or RiTUAL Lab. Visit our group website to learn more about what we do at UH.


My research is currently funded by ONR and NSF. I received an NSF CAREER award in 2014 for my work on authorship attribution in cross-domain settings.