STEM Ed PRF: Understanding and Improving Undergraduate Computer Science Regulation, Performance, and Motivation Using Digital Traces and Technologies

该奖项全部或部分由2021年美国救援计划法案（公法117-2）资助。该博士后研究项目将专注于利用教育数据挖掘来了解计算机科学入门课程的本科生如何利用他们的激励资源并规范学习。本研究旨在探讨学生的学习动机与自我调节学习之间的互动关系。初步调查结果，然后预计将通知创建一个及时的学习干预，旨在改善学习模式。该项目还旨在通过提高学生的学习和动机，增加妇女和有色人种学生在计算机科学领域的参与，这可能会导致该领域更高的持久性和学位获得率。学生的学习是一个动态的、特定于情境的过程。目前旨在促进STEM的持久性和表现的干预措施在广泛的背景下捕捉学生的学习，而不是在学生参与课程的那一刻。本项目旨在使用多种数据源（包括数字跟踪数据）更准确和全面地了解计算机科学本科生的学习情况。这些数据有可能捕捉学生学习和动机的动态本质。博士后研究员选择在“自我调节学习的元认知和情感模型”（Efklides，2011）的框架内定位她的工作。然后，该研究员将探索动机，行为和学习之间的联系，在任务和人的水平，并贡献新的见解，认为动机和自我调节的学习之间的相互作用的互动水平的基础理论。此外，该项目将使用A/B方法来测试作为项目一部分创建的干预措施，该项目侧重于及时的自我调节学习支持，以改善学习模式。动机和自我调节学习信息的A/B测试可能允许对结构和性能之间的联系做出更强有力的声明。将这些方法结合在同一个项目中，对于计算机科学本科生有效使用学习分析具有变革性的潜力。该项目响应STEM教育博士后研究奖学金（干艾德PRF）计划，旨在提高研究知识，技能，并在干，干教育，教育，该奖项反映了NSF的法定使命，并被认为是值得支持的，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。

This award is funded in whole or in part under the American Rescue Plan Act of 2021 (Public Law 117-2).This postdoctoral fellowship research project will focus on leveraging educational data mining to understand how undergraduate students in introductory Computer Science courses draw on their motivational resources and regulate learning. The study seeks to explore ways in which students’ motivation interacts with self-regulated learning. Initial findings are then expected to inform the creation of a just-in-time learning intervention designed to improve study patterns. This project also aims to increase participation for women and students of color in Computer Science by enhancing student learning and motivation which may result in greater rates of persistence and degree attainment in the field. Student learning is a dynamic and context-specific process. Current interventions designed to promote persistence and performance in STEM capture student learning in broad contexts rather than in the moment students engage with their coursework. This project aims to gain a more accurate and comprehensive view of undergraduates’ learning in Computer Science using multiple data sources, including digital trace data. These data have the potential to capture the dynamic nature of student learning and motivation. The postdoctoral fellow has chosen to position her work within the framework of the “Metacognitive and Affective Model of Self-Regulated Learning” (Efklides, 2011). The fellow will then explore connections between motivation, behavior, and learning at both the task and person level and contribute new insights into that foundational theory that consider the interplay between motivation and self-regulated learning across levels of interaction. In addition, this project will use A/B methods to test an intervention created as part of the project that focuses on just-in-time, self-regulated learning support to improve study patterns. The A/B testing of motivation and self-regulated learning messages may allow for stronger claims to be made about the links between constructs and performance. Combining these methods within the same project has transformative potential for the effective use of learning analytics by Computer Science undergraduate students. The project responds to the STEM Education Postdoctoral Research Fellowship (STEM Ed PRF) program that aims to enhance the research knowledge, skills, and practices of recent doctorates in STEM, STEM education, education, and related disciplines to advance their preparation to engage in fundamental and applied research that advances knowledge within the field.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.