The Tutor Engagement Assistant (TEA): Promoting High-Quality TA-Student Interactions

导师参与助理 (TEA)：促进高质量的助教与学生互动

• 批准号: 2214538
• 负责人: Caitlin Kelleher
• 金额: $ 20.04万
• 依托单位: Washington University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-07-01 至 2024-06-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2214538&HistoricalAwards=false
• 关键词: Tutor; Engagement; Assistant; TEA; Promoting

This project aims to serve the national interest by developing a new software tool to support teaching assistant (TA)-student interactions. Increasing class sizes in computing have led to a greater reliance on undergraduate TAs to support student learning. Many TAs are often only slightly more experienced than the students they help. Providing help to a learner is a complex cognitive process that requires: 1) Understanding the problem, 2) Debugging the learner's incorrect solution, 3) Identifying conceptual gaps, and 4) Determining how to best fill the conceptual gaps. The goal of this project is the development of the Tutor Engagement Assistant (TEA) system. The TEA system will help undergraduate TAs to quickly debug student code and construct personalized problem sets to structure their interactions with students. This project hopes to lead to more efficient and educationally effective TA help in computing courses nationwide, and should contribute to research in the learning sciences, HCI, and computing education. This work is based on two theories: social constructionism and cognitive load. It draws on the ICAP framework that links cognitive engagement with active learning outcomes. The project will explore the impact of TEA on time on task, type of help, cognitive load, learner engagement, self-efficacy, attitude towards help, help-seeking behavior, and learning. The research plan consists of three phases: 1) baseline data collection, 2) formative evaluation, and 3) TEA deployment. The project will lead to 1) a detailed understanding of tutor-student interactions through observation studies, 2) new approaches to help tutors quickly understand student errors via a guided walkthrough of automatically generated corrections, 3) techniques for identifying and curating personalized problem sets for students, and 4) an evaluation of the impact of personalized problem sets on the quality of tutor-student interactions and student learning. 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.

该项目旨在通过开发一种新的软件工具来支持助教（TA）与学生的互动，从而为国家利益服务。随着计算机课程班级规模的不断扩大，越来越多的本科生助教来支持学生的学习。许多助教通常只比他们帮助的学生更有经验一点。向学习者提供帮助是一个复杂的认知过程，需要：1)理解问题，2)调试学习者的错误解决方案，3)识别概念空白，4)确定如何最好地填补概念空白。这个项目的目标是开发导师参与助理（TEA）系统。TEA系统将帮助本科助教快速调试学生的代码，并构建个性化的问题集，以组织他们与学生的互动。该项目希望在全国范围内的计算机课程中提供更高效、更有效的助教帮助，并对学习科学、HCI和计算机教育的研究做出贡献。本研究基于两种理论：社会建构论和认知负荷理论。它借鉴了ICAP框架，将认知参与与主动学习成果联系起来。本项目将探讨TEA对任务完成时间、帮助类型、认知负荷、学习者参与、自我效能、对帮助的态度、寻求帮助行为和学习的影响。研究计划包括三个阶段：1)基线数据收集，2)形成性评估，以及3)TEA部署。该项目将导致：(1)通过观察研究详细了解导师与学生之间的互动；(2)通过引导自动生成的更正来帮助导师快速了解学生错误的新方法；(3)为学生识别和管理个性化问题集的技术；(4)评估个性化问题集对导师与学生互动质量和学生学习的影响。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。

项目成果

An Algorithm for Generating Explainable Corrections to Student Code

一种对学生代码生成可解释的更正的算法

• DOI: 10.1145/3564721.3564731
• 发表时间: 2022
• 期刊: Proceedings of the 22nd Koli Calling International Conference on Computing Education Research
• 作者: Malysheva, Yana;Kelleher, Caitlin
• 通讯作者: Kelleher, Caitlin