Synthesis and Design Workshop: Weaving the Fabric of Adaptive STEM Learning Environments Across Domains and Settings

本次研讨会由“亲爱的同事来信：数字科学、技术、工程和数学(STEM)学习环境的设计原则”(NSF 18-017)资助。本次研讨会的目标是为不同领域和环境的不同学习者阐明未来STEM学习的变革性愿景。它在新兴的(A)学习科学、(B)评估和(C)大数据之间建立了联系，以制定设计STEM学习环境的框架和工具。该项目采取公平优先的方法，通过创新的设计扩大参与，召集跨学科团队制作一份白皮书，提出具有前瞻性的数字增强的STEM环境，架起正式和非正式学习环境的桥梁，并回应每个学习者的需求。白皮书还将阐明未来的研究议程，这可能会导致人类技术前沿的新突破。公开邀请的设计研讨会位于斯坦福大学，并通过公共网站和社区外联活动在这些学术团体聚集的关键会议上传播，将确保教育工作者、研究人员和分析人员广泛了解并获得这些模型、工具、框架、设计原则和研究优先事项。该研讨会旨在与学习科学、心理测量学和计算机科学建立必要的新合作，以设计具有强大的过程中自适应学习措施的综合STEM学习环境，以解决更深层次学习的关键方面。它召集创新者在以股票为重点的技术增强型STEM学习、教育数据挖掘和学习分析以及计算心理测量学方面推进最先进的技术，以开发创新的方法来设计和扩展大数据时代综合STEM学习的未来。在这些学科观点的交叉点上，将从项目活动中产生生成性新算法和知识模型、心理测量模型和学习者途径模型的基础设施，以通过结合来自多模式学习分析的信号和用于多方面衡量学术能力的软件来改变学习和评估设计。项目范围将以三个问题为指导：(1)整合STEM学习的学习环境如何在不同的学生群体中扩大成功的努力，并在正式和非正式学习背景之间架起桥梁？(2)需要什么创新的研究方法、统计技术和建模形式主义来将理论模型嵌入数据驱动的计算方法中，以便捕获、表征和支持关于个人和基于团队的学习的因果主张，特别是对于复杂的、多源流数据？(3)如何为STEM科目的综合学习和评估创建多领域线程化学习进展？该奖项反映了NSF的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

This workshop is funded through the "Dear Colleague Letter: Principles for the Design of Digital Science, Technology, Engineering, and Mathematics (STEM) Learning Environments (NSF 18-017)." The goal of this workshop is to articulate a transformative vision of future STEM learning for diverse learners across domains and settings. It forges a nexus among the emerging (a) sciences of learning, (b) assessment, and (c) big data to formulate frameworks and tools for designing STEM learning environments. Taking an equity-first approach for broadening participation through innovative designs, this project convenes interdisciplinary teams to produce a white paper proposing forward-looking digitally-augmented STEM environments that bridge formal and informal learning contexts and are responsive to the needs to every learner. The white paper will also articulate a future research agenda that could lead to new breakthroughs at the Human-Technology Frontier. The open-invitation design workshop, strategically located at Stanford University, and dissemination through a public website and community outreach activities at key conferences in which these scholarly communities convene will ensure broad awareness of and access to these models, tools, frameworks, design principles, and research priorities for educators, researchers, and analysts. The workshop is designed to construct needed new collaborations with the learning sciences, psychometrics, and computer science to design integrative STEM learning environments with robust in-process measures of adaptive learning that address key aspects of deeper learning. It convenes innovators advancing the state-of-the-art in equity-focused, technology-enhanced STEM learning, educational data mining and learning analytics, and computational psychometrics, to develop innovative ways to design and scale for a future of integrated STEM learning in an era of big data. An infrastructure of generative new algorithms and knowledge models, psychometric models, and learner pathway models will emerge from project activities at the intersection of these disciplinary perspectives to transform learning and assessment designs by incorporating signals from multimodal learning analytics and software for multi-faceted measurement of academic competencies. The project scope will be guided by three questions: (1) How can learning environments for integrated STEM learning scale successful efforts across diverse student populations and bridge formal and informal learning contexts? (2) What innovative research methods, statistical techniques and modeling formalisms are necessary to embed theoretical models in data-driven computational approaches in order to capture, characterize and support causal claims about individual and team-based learning, especially for complex, multi-source streaming data? (3) How can multi-domain threaded learning progressions be created for integrated learning and assessment of STEM subjects?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.