Supporting collaborative reflection by K-12 teachers with analytics from intelligent tutoring software

K-12教师从事终身专业学习的一种方式是反思自己的实践，例如通过回顾课堂上的视频记录。过去的研究表明，反思对教师的课堂实践具有强大的影响。过去的另一项研究表明，学生使用基于人工智能的智能辅导软件（ITS）学习效果非常好，例如，在初中和高中数学方面，教师的支持有助于这种效果。如果教师能够定期地反思他们的课堂实践中关于这种类型的软件，那么他们很可能能够更有效地帮助学生。然而，有效的反思受到这样一个事实的阻碍，即教师几乎不可能注意到并记住在任何给定的课堂上发生的所有事情。一个设计良好的工具可以展示从课堂中提取的分析，这可能会有很大的帮助。因此，目前的研究探讨了如何设计一种分析工具，以支持K-12教师与可信赖的同事一起反思他们在学生使用智能辅导系统（ITS）的课堂实践。该项目将建立一个创新的工具，使计算机能够自动收集和分析多个数据源（即多模式分析）。该工具将促进教师之间的反思和讨论，例如关于学生的学习进展或挑战，以及他们自己对某些学生或学生群体的可能隐含的偏见。通过对数据的反思，教师可以找到改善教学实践、学生学习和课堂公平的方法。该项目的主要目标是设计和创建这样一个工具，测试它是否支持教师之间有效的协作反思，以及它是否能改善课堂实践。该项目将有助于实现使分析对教师有用这一更广泛的目标。它有潜力改善一种非常有效的K-12课堂教学形式，即使用ITS学习，这是一种越来越普遍的学习环境。该项目将设计、创建并试点测试一种新的分析工具，以支持教师共同反思他们围绕智能交通的课堂实践。该工具将利用多模式分析；它将提取和显示学生学习和教师实践的趋势，并从其自己的数据存储中策略性地选择例子来说明这些趋势，这些数据存储是在its会议期间记录的。该工具将利用(1)位置数据，通过放置在教室中的传感器收集，揭示教师在教室中的运动模式；(2)生理数据，通过教师佩戴的生理腕带收集，揭示他们的压力水平对学生的影响方式；(3)详细记录学生与辅导系统互动的数据，分析以检测进步、挣扎、知识增长和学习行为。(4)捕捉课堂互动重要细节的视频数据。反思工具将与中学教师一起设计。教师将从头到尾参与研究，以确保该工具符合他们的偏好和需求。设计将以经过验证的教师反思模型为指导，该模型适用于ITS会议的多模式分析。该工具将在CTAT+Tutorshop中实施，CTAT+Tutorshop是一个广泛使用的智能交通研究和开发平台。许多所需的分析已经存在于CTAT+Tutorshop中，但新的分析也将被开发出来。随着时间的推移，该工具将不断改进和试点测试。最后，老师们将在他们的班级中测试一个教室准备好的原型。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。

One way K-12 teachers engage in lifelong professional learning is by reflecting on their own practices, for example by reviewing video recordings from their class sessions. Past research shows that reflection has powerful effects on teachers’ classroom practice. A separate line of past research shows that students learn very well with AI-based intelligent tutoring software (ITS), for example, in middle-school and high-school mathematics, and that teachers' support contributes to this effect. It is likely that teachers could help students more effectively if they were to periodically reflect on their classroom practices with regard to this type of software. Yet effective reflection is hampered by the fact that it is nearly impossible for teachers to notice and remember all that happens during any given classroom period. A well-designed tool that presents analytics extracted from class sessions could be a great help. The current research therefore investigates how to design an analytics tool that can support K-12 teachers in reflecting collaboratively with trusted colleagues on their classroom practices around students’ work with intelligent tutoring systems (ITS). The project will build an innovative tool that allows computers to automatically collect and analyze multiple sources of data (i.e., multimodal analytics). The tool will prompt reflection and inform discussion among teachers, for example about their students’ learning progress or challenges, and about their own, possibly implicit, biases towards certain students or groups of students. Through reflection with data, teachers can identify ways to improve their teaching practices, student learning, and equity in their classrooms. The main goal of the project is to design and create such a tool, test whether it supports effective collaborative reflection among teachers, and whether it leads to improved classroom practices. The project will contribute to the broader goal of making analytics useful for teachers. It has the potential to improve a highly effective form of K-12 classroom instruction, namely, learning with ITS, an increasingly common learning environment. The project will design, create, and pilot-test a new analytics tool for supporting teachers in jointly reflecting on their classroom practices around ITS. The tool will leverage multimodal analytics; it will extract and show trends in students’ learning and teachers’ practices and illustrate them with strategically selected examples from its own data store, recorded during ITS sessions. The tool will take advantage of (1) location data, collected with sensors placed in classrooms, to reveal patterns in teachers’ movement in the classroom, (2) physiological data, collected with physiological wristbands worn by teachers, to reveal ways in which their stress level affects students, (3) log data detailing students’ interactions with the tutoring system, analyzed to detect progress, struggles, knowledge growth, and learning behaviors, and (4) video data that capture important detail about classroom interactions. The reflection tool will be designed with middle-school teachers. Teachers will be involved in the research start-to-finish to make sure the tool matches their preferences and needs. The design will be guided by a proven model of teacher reflection, adapted for multimodal analytics from sessions with an ITS. The tool will be implemented within CTAT+Tutorshop, a widely-used platform for ITS research and development. Many of the needed analytics already exist within CTAT+Tutorshop, but new ones will be developed as well. Over time, the tool will be continuously improved and pilot tested. At the end, teachers will test a classroom-ready prototype with their classes.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.