The project team will develop a new software product for use with StepWise AI, a product developed with previous ED/IES SBIR awards, to assist students with math word problems. The new product will implement effective methods for students to tackle math word problems through the use of Natural Language Processing (NLP) software, Self- Regulated Strategy Development (SRSD) techniques, and research-based algorithms. The StepWise Virtual Tutor uses artificial intelligence (AI) to personalize tutoring and assessment for Algebra. The product facilitates students in exploring many valid pathways to a solution and the system tracks each step in students' work, catches algebraic and arithmetic errors, and provides hints and presents information to educators. This Phase I project team will develop a prototype of a new natural language processing and machine learning component that will provide instantaneous feedback to students as they solve math word problems, including hints prior to a student setting up a word problem. The prototype will also include a dashboard to present educators with insights on student progress. At the end of Phase I, the project team will conduct a pilot study with four educators and 24 high school students to test if the prototype functions as planned, whether students receive just-in-time hints and supports while completing word problems, and whether educators believe that the information generated by the dashboard is useful and appropriate for providing individualized instruction for each student.
