I am the Research Director of the Natural Language Processing Group in Research & Development at Educational Testing Service in Princeton, New Jersey. My research interests span natural language processing for educational technology, automated essay scoring and evaluation, discourse and sentiment analysis, argumentation mining, education policy, English language learning, and writing research. The intersection of my interests has led to these two inventions: E-rater®, an automated essay evaluation application, and Language MuseSM, an instructional authoring tool for teachers of English learners. The Language Muse Activity PaletteTM -- a new classroom tool under development targeting English learners-- automatically generates language activities for learning vocabulary, sentence structure, and discourse elements in classroom texts. I co-organize this yearly workshop (usually at NAACL or ACL): Innovative Use of NLP for Building Educational Applications (with Joel Tetreault and Claudia Leacock).
Application-wise, my research focus targets designing NLP-centered systems for the service of learning. I have significant experience managing system design from the early idea stages through product implementation. I believe that working with users from the very early stages is critical, and this is also one of my favorite aspects of system design. In this context, I have spent a lot of time collaborating with K-12 instructors and university faculty. I spend a lot of time reading about the Common Core State Standards Initiative and working with university faculty and administration to inform my thinking about building new systems that support writing instruction and assessment - both in K-12 and Post-Secondary settings. I think that Understanding Language is a great initiative with a great group of people that illustrates the critical role of language in the Common Core Standards, especially with regard to English learners, and addresses important policy issues about equity in education.
I have become increasingly more engaged in automated writing evaluation and writing research, advocating for building capabilities that cover a greater breadth of genres and relevant writing constructs to improve support for writing instruction and assessment.
1. Department of Education, Institute of Education Sciences, Education Technology Program, Grant Award # R305A140472 , Goal #2: Technology-Assisted Generation of Linguistically-Relevant Instructional Activities to Support ELLs in Content and Language Learning in the Content Areas, $1,499,000, Principal Investigator (with Co-PI, John Sabatini) (July 2014 - July 2017).
2. Department of Education, Institute of Education Sciences, Education Technology Program, Grant Award #R305A100105, Goal #2: A Technology-Rich Teacher Professional Development Intervention that Supports Content-Based Curriculum Development for English Language Learners, $1,499,000, Principal Investigator. (March 2010 - March 2014).
Burstein, J., Elliott, N., and Molloy, H. (in press). Informing Automated Writing Evaluation Using the Lens of Genre: Two Studies. To appear in Special Issue: CALICO Journal 33.1, 2016 (Guest Editors: Volker Hegelheimer, Ahmet Dursun, Zhi Li).
Shermis, M., Burstein, J., Elliot, N., Miel, S., and Foltz, P. (in press). Automated Writing Evaluation: A Growing Body of Knowledge. In the Handbook of Writing Research (Eds. C. MacArthur, S. Graham, and J. Fitzgerald): Guilford Press: NY.
Farra, N., Somasundaran, S., and Burstein, J. (2015). Scoring Persuasive Essays Using Opinions and their Targets. The 10th Workshop on Innovative Use of NLP for Building Educational Applications, NAACL 2015, Denver, CO, 64-74.