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

该项目的目标是开发cuellearn，这是一个教育网络应用程序，将促进有效的同伴协作，以提高中学生的数学问题解决能力。研究表明，当学生参与到良好的、共享的、合作的学习经历中时，学习往往会更好、更持久。然而，教育技术并不经常利用这项研究，其重点往往是在个人而不是一个群体。因此，CueLearn项目将开发、测试和实施两种智能策略，以提高学生的协作解决问题能力：1)通过在CueLearn中创建有效的同伴小组，促进有效的学生协作；2)使用实时支持，提高学生的参与度，帮助学生高效地坚持学习。该项目的主要目标是设计一个系统，方便所有学生进行高质量的同伴协作，同时支持教师使用技术进行协作工作。该项目通过自动分配学生与优化的同伴小组一起工作，重点关注社会学习体验。多种分组策略将通过一系列观察性研究和实验进行测试，以确定哪种分组策略效果最好。例如，学生可以根据他们想要解决问题的策略进行分组，这样学生就可以接触到使用不同策略的同龄人的不同方法。然而，智能的学生分组方法可能对他们自己的学习没有效果，除非在解决问题的过程中为学生提供额外的支持。因此，机器学习方法将被用于监控参与度，并实时检测非生产性的持久性形式，以便在需要时提供即时支持。重要的是，这些支持将与学生共同设计。假设自动化理想分组与即时支持相结合可以提高学生的问题解决能力和数学信念。通过所有这些设计创新，该项目旨在为学生和教师提供一种新的有效的教育技术。探索研究preK-12项目（DRK-12）旨在通过研究和开发创新资源、模型和工具，显著提高preK-12学生和教师对科学、技术、工程和数学（STEM）的学习和教学。DRK-12计划中的项目建立在STEM教育的基础研究和先前的研究和开发工作的基础上，为拟议的项目提供了理论和实证依据。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

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.