NSF Award
1812660
Many teachers want to adapt their instruction to meet student learning needs, yet lack the time to regularly assess and analyze students' developing understandings. The Supporting Teachers in Responsive Instruction for Developing Expertise in Science (STRIDES) project takes advantage of advanced technologies to support science teachers to rapidly respond to diverse student ideas in their classrooms. In this project students will use web-based curriculum units to engage with models, simulations, and virtual experiments to write multiple explanations for standards-based science topics. Advanced technologies (including natural language processing) will be used to assess students' written responses and summaries their science understanding in real-time. The project will also design planning tools for teachers that will make suggestions relevant research-proven instructional strategies based on the real-time analysis of student responses. Research will examine how teachers make use of the feedback and suggestions to customize their instruction. Further we will study how these instructional changes help students develop coherent understanding of complex science topics and ability to make sense of models and graphs. The findings will be used to refine the tools that analyze the student essays and generate the summaries; improve the research-based instructional suggestions in the planning tool; and strengthen the online interface for teachers. The tools will be incorporated into open-source, freely available online curriculum units. STRIDES will directly benefit up to 30 teachers and 24,000 students from diverse school settings over four years. The Discovery Research K-12 program (DRK-12) seeks to significantly enhance the learning and teaching of science, technology, engineering and mathematics (STEM) by preK-12 students and teachers, through research and development of instructional innovations. Projects in the DRK-12 program build on fundamental research in STEM education and prior research and development efforts that provide theoretical and empirical justification for proposed projects. <br/><br/>Leveraging advances in natural language processing methods, the project will analyze student written explanations to provide fine-grained summaries to teachers about strengths and weaknesses in student work. Based on the linguistic analysis and logs of student navigation, the project will then provide instructional customizations based on learning science research, and study how teachers use them to improve student progress. Researchers will annually conduct at least 10 design or comparison studies, each involving up to 6 teachers and 300-600 students per year. Insights from this research will be captured in automated scoring algorithms, empirically tested and refined customization activities, and data logging techniques that can be used by other research and curriculum design programs to enable teacher customization.<br/><br/>This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
