CAREER: Designing for Learning at the Intersection of Sports, Analytics and Physical Computing

西北大学将设计以运动为中心的学习体验，帮助学生运动员看到计算在体育运动中的相关性。该项目将侧重于将计算机科学与体育运动联系起来的方法，并将努力揭示有效鼓励有色人种学生运动员参与青少年课后和校外体育运动的计算机科学的策略。认识到教练在学生运动员的发展中发挥的重要作用，研究小组将与学生运动员和教练进行访谈，以更好地了解他们对计算机科学的看法。这些采访还将涉及青少年体育项目已经使用技术的方式。项目团队将利用这些信息来设计新的工具和活动，反映学生运动员和教练的偏好和看法。该研究团队还将组织课后和夏季充实计划，向运动员和教练传授设计体育相关技术的令人兴奋的机会。一些经验将教参与者设计运动可穿戴设备，机器学习和数据科学。最后，研究小组将使用人工智能来评估这些面向参与者的活动中的学习。通过利用大量参与体育运动的年轻人，研究小组希望确定一种可能的策略，以扩大对计算机科学的参与。该项目基于STEM激活框架，该框架考虑了魅力，能力信念，价值观，科学意义和参与者参与的融合。具体来说，该项目将参与田径运动定位为学习计算机科学的一项资产。此外，该项目旨在通过开发支持以运动员为中心的计算机科学学习体验所需的教学，技术和分析工具来打破体育和学术之间的流行二分法。教学工具包括新颖的学习活动，将数据科学，工程设计，机器学习和物理计算与体育联系起来。这些技术工具包括适合学生年龄的、可访问的界面，用于收集、可视化学生收集的多模态数据并从中得出推论。技术工具还包括支持学生使用物理计算设计和构建定制可穿戴设备。最后，分析工具利用PI在多模态学习分析（MMLA）方面的专业知识，通过自动化特征提取和数据注释来扩展和扩展STEM激活框架的观察和参与协议的元素。该项目采用迭代的、以用户为中心的和基于设计的研究方法来实现这些目标和活动。这项工作有助于研究1）开发和支持新的途径，以计算职业生涯，2）设计和实施的工具，促进收集，分析和学习与多模态数据和物理计算，和3）利用多模态分析，以确定新的方式来表征学习和参与非该奖项反映了NSF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。

Northwestern University will design athletic-centered learning experiences that help student-athletes see the relevance of computing in athletics. This project will focus on ways for connecting computer science with athletics, and will work to uncover strategies for effectively encouraging participation of student-athletes of color in computer science in youth after-school and out-of-school athletics. Recognizing the important role that coaches play in the development of student-athletes, the research team will conduct interviews with both student-athlete and coaches to better understand their perceptions of computer science. These interviews will also touch on the ways that the youth sports programs are already using technology. The project team will use this information to design new tools and activities that reflect the preferences and perceptions of student-athletes and coaches. The research team will also organize after-school and summer enrichment programs to teach athletes and coaches about the exciting opportunities for designing sports-related technologies. Some of the experiences will teach participants about designing sports wearables, machine learning and data science. Finally, the research team will use artificial intelligence to assess learning within these participant-facing activities. By tapping into the large number of youth participating in sports, the research team hopes to identify a possible strategy for broadening participation in computer science. This project is grounded in the STEM activation framework, which considers the confluence of fascination, competency beliefs, values, scientific sensemaking and participant engagement. Specifically, the project positions participation in athletics as an asset for learning computer science. Moreover, the project aims to disrupt the popularized dichotomy between athletics and academics by developing the pedagogical, technological and analytic tools needed to support athletic-centered computer science learning experiences. The pedagogical tools include novel learning activities that bridge data science, engineering design, machine learning and physical computing, with athletics. The technological tools include age-appropriate and accessible interfaces for collecting, visualizing and drawing inferences from the multimodal data that students collect. Technological tools also include supporting students in designing and building custom wearables using physical computing. Finally, the analytic tools leverage the PI’s expertise in Multimodal Learning Analytics (MMLA) to extend and scale elements of the STEM Activation Framework’s Observation and Engagement Protocol via automated feature extraction and data annotation. The project uses an iterative, user-centered and design-based research approach to realize these goals and activities. This work contributes to research on 1) developing and supporting novel pathways to computing careers, 2) the design and implementation of tools that facilitate collecting, analyzing and learning with multimodal data and physical computing, and 3) leveraging multimodal analytics to identify new ways to characterize learning and engagement in non-traditional learning environments.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.