Improving the Quality of Teaching Assistant Feedback to Undergraduate Students in Introductory Computer Science Courses

该项目旨在通过调查现有的提交和反馈交付系统与助教（TA）培训的整合，为国家利益服务。具体来说，这项工作将探索使用自然语言处理技术为助教提供反馈，就像他们为学生在计算机科学入门课程中的工作提供书面反馈一样。该计划将探讨不同的方法，以直接指导有效的反馈实践和文化响应教学方法来培训助教。随着计算机班级规模的增长快于教师招聘，这项工作有可能满足助教提供高质量反馈的日益增长的需求。低质量的反馈已被证明会对学生的成功和继续学习这门学科的意愿产生负面影响。因此，提高计算机课程中助教反馈的质量可以帮助更多的学生成功进入计算机行业。集成的提交和助教培训系统将由一个服务器组成，该服务器通过定制的插件与集成开发环境通信，以促进学生、教师和助教之间的课堂交流。人机交互技术将用于设计不显眼的仪表板，使教师能够有效地监控助教的反馈。该项目的研究计划将调查新的培训系统如何改变助教的观点，改变反馈实践，并影响本科生的学习。该项目还将研究数据可视化策略，以便有效地监测TA的性能。交付成果将包括一系列的助教培训模块、一个助教反馈样本数据集（包括学生评分）、一个识别有用或无用反馈的自然语言处理分类器，以及一个向教师展示助教反馈表现的仪表板。NSF IUSE: EHR计划支持研究和开发项目，以提高所有学生STEM教育的有效性。通过参与学生学习轨道，该计划支持有前途的实践和工具的创建，探索和实施。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。

This project aims to serve the national interest by investigating the integration of existing submission and feedback delivery systems with teaching assistant (TA) training. Specifically, this work will explore the use of natural language processing techniques to provide feedback to TAs as they provide written feedback about students’ work in introductory computer science courses. The project will investigate different ways to train TAs with direct instruction on effective feedback practices and culturally responsive teaching methods. This work has the potential to address the growing need for TAs to provide high-quality feedback, as computing class sizes are growing faster than faculty hiring. Low-quality feedback has been shown to negatively impact student success and willingness to continue in the discipline. Thus, improving the quality of TA feedback in computing courses could help more students to successfully enter the computing workforce.The integrated submission and TA training system will consist of a server that communicates with an Integrated Development Environment via custom-built plug-ins to facilitate in-class communication between students, instructors, and TAs. Human-computer-interaction techniques will be used to design unobtrusive dashboards that will enable instructors to efficiently monitor TA feedback. The project’s research plan will investigate how the new training system changes TA perspectives, alters feedback practices, and affects undergraduate learning. The project will also investigate strategies for data visualization that enable efficient monitoring of TA performance. The deliverables will include a series of TA training modules, a dataset of TA feedback samples together with student ratings, a natural language processing classifier that recognizes helpful or unhelpful feedback, and a dashboard that shows TA feedback performance to instructors. The NSF IUSE: EHR Program supports research and development projects to improve the effectiveness of STEM education for all students. Through the Engaged Student Learning track, the program supports the creation, exploration, and implementation of promising practices and tools.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.