Kinga Dobolyi

Associate Professor of Practice
Department of Computer Science (preferred over phonecall)

Office: SEH 4655

Office hours: SEH 4655 Tuesdays from 12:45pm-2:00pm, Zoom on Wednesdays 8:45am-10:00am, or by appointment (please email)

Phone: 202-994-4109 (please email instead)

Research Interests

  • Computer vision and NLP applied to biomedical challenges
  • Software Testing
  • Computer Science education

I joined GWU in the fall of 2021, having previously taught computer science at George Mason University for eight years. My interests in computer science education focus on how to retain and increase the number of students in such courses, especially under-represented groups, via techniques such as self-pacing, active learning, test-driven development, automated feedback, student-led discussions, and focusing on non-traditional computer science applications. I have also worked in industry as a data scientist at a startup, and as an applied deep learning researcher at the non-profit IQT Labs, specializing in biomedical applications of computer vision and NLP. My current research interests include automated testing for deep learning models and characterizing uncertainty in research on emerging infectious diseases.

  • Ph.D. in Computer Science, University of Virginia, 2010
  • B.S. in Computer Science, University of Maryland, 2004

My focus at GW is primarily teaching, but I also conduct research with undergraduate and graduate students in various areas of NLP and Computer Vision. If you are interested in working with me on a research project, send me an email. Please note that I do not support PhD students as their thesis advisor, I do not work with students over the summer, and I have very limited bandwidth to take on research projects each semester (between 0-2 groups).

Current research group on NLP with COVID-19 academic articles: Previous researchers and publications:
  • Grady McPeak, "Improving BERT Classification Performance on Short Queries About UNIX Commands Using an Additional Round of Fine-Tuning on Related Data," 2022 IEEE 16th International Conference on Application of Information and Communication Technologies (AICT), Washington DC, DC, USA, 2022, pp. 1-5, doi: 10.1109/AICT55583.2022.10013532.

Image from

Covid Hindsight2020: Characterizing uncertainty in academic literature on emerging infectious disease outbreaks


Image from

Computer Vision for analyzing organ-on-a-chip viability in hepatocyte cultures


Can Human Judgement Aid Knowledge Discovery Algorithms?

Evaluating BERT to build a scientific sentiment model of sentences.

Software Reliability and Security
Image from

Software Testing and Web Fault Severity