Jill Burstein, Director of Research of the Natural Language Processing Group in the Research Division at Educational Testing Service
Abstract: Writing is a challenge, especially for at-risk students who may lack the prerequisite writing skills required to persist in U.S. 4-year postsecondary (college) institutions. U.S K-12 research examines writing achievement and the specific skills and knowledge in the writing domain. Automated writing evaluation (AWE) systems typically support the measurement of pertinent writing skills for automated scoring of large-volume, high-stakes assessments and online instruction. AWE has been used primarily for on-demand essay writing on standardized assessments. However, the real-time, dynamic nature of NLP-based AWE affords the ability to generate feedback across a range of writing genres in postsecondary education, such as, on-demand essay writing tasks, argumentative essays from the social sciences, and lab reports in STEM courses. AWE analyses can be use to generatefeedback that can provide students with meaningful information to support their writing, and educational analytics that can be informative for various stakeholders, including students, instructors, parents, administrators and policy-makers. This talk will focus on a demonstration and discussion of new publicly-accessible feedback app (to be announced) and an exploratory research study that uses AWE to examine relationships between features in postsecondary student writing and broader success predictors.