Collaborative Research: CueLearn: Enhancing Social Problem Solving through Intelligent Support

The goal of this project is to develop CueLearn, an educational web application that will foster effective peer collaborations to improve mathematical problem solving amongst middle school students. Research suggests that learning is often better and longer lasting when students engage in well-scaffolded, shared, and collaborative learning experiences. However, educational technologies do not often leverage this research, with the focus most often being on the individual rather than a group. The CueLearn project will thus develop, test, and implement two intelligent strategies to improve students' collaborative problem solving: 1) facilitating effective student collaborations through the creation of effective peer groups within CueLearn, and 2) using real-time supports to increase student engagement and help students persist productively. The project's key aim is to design a system that will easily facilitate quality peer collaboration for all students, while also supporting teachers in their use of technology for collaborative work. The project focuses on social learning experiences by automatically assigning students to work with optimized peer groups. Multiple grouping strategies will be tested through a series of observational studies and experiments to identify which grouping strategy works best. For example, students may be grouped based on their intended problem-solving strategy, so that students will be exposed to diverse approaches from peers who are using different strategies. However, intelligent student grouping methods may not be effective for learning by themselves, unless students are also provided with additional support during problem solving. Machine learning approaches will therefore be used to monitor engagement and detect unproductive forms of persistence in real-time in order to provide in-the-moment support as needed. Critically, these supports will be co-designed with students. Automated ideal grouping combined with just-in-time supports are hypothesized to improve students' problem solving performance and mathematical beliefs. Through all of these design innovations, the project aims to provide a new and effective educational technology for students and teachers. The Discovery Research preK-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 innovative resources, models and tools. 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. 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.