BCC: Community and Capacity for Educational Discourse Research

在线学习环境正在迅速扩大可收集的有关学生学习机会和学习过程细节的数据的性质。随着高中、社区学院和大学招收更多的学生参加混合课程或在线课程，有关学生正在做什么的数据量超过了典型的教育研究方法。借鉴多种传统，教育话语数据分析解决了教育中的多个长期存在的问题，包括开发出更好地预测学生在课程期间成功的方法，并设计干预措施以提供支持。这项提议中的研究人员将建立一个社区，以解决三个重要领域：数据共享中的道德问题；数据共享中的技术问题；以及计划建立一个基础设施来支持和发展这两个领域的能力。在这一努力中建立的社区将共同为数据集和工具创建必要的元数据和标准，为适当批准使用在线话语数据提供模板，以及可在数据平台上共享的去身份识别算法。这项研究将通过两个相互关联的讲习班进行，通过规划与专家咨询委员会的会议进行分析。最初的研讨会将侧重于教育话语和本科生的经历，以确定围绕支持合作教育话语研究所必需的基础设施的问题。第二期研讨会将侧重于使用来自大规模在线公开课(MOOC)的话语数据的具体基础设施需求。将编写和分发一份白皮书，讨论伦理和技术问题和解决办法，以及促进协作教育话语研究的基础设施需求。

Online learning environments are rapidly expanding the nature of the data that can be collected about student opportunity to learn and the details of the learning process. As high schools, community colleges and universities enroll more students in blended or online courses, the volume of data about what students are doing surpasses typical educational research methodologies. Borrowing from multiple traditions, analysis of educational discourse data addresses multiple persistent problems in education, including the development of ways to better predict student success during a course and to design interventions to provide support. The researchers in this proposal will build a community to address three important areas: ethics in data sharing; technical issues in data sharing; and, plans for an infrastructure to support and develop capabilities in both of these. The community built in this effort will collaboratively create the necessary metadata and standards for data sets and tools, templates for appropriate approval to use online discourse data, and de-identification algorithms that can be shared across data platforms. The research will be conducted through two interrelated workshops parsed by planning meetings with an expert advisory board. An initial workshop will focus on educational discourse and the undergraduate experience to identify the issues around the infrastructure necessary to support collaborative education discourse research. The second workshop will focus on the specific infrastructure needs for working with discourse data from massive open online courses (MOOCs). A white paper will be constructed and disseminated that addresses ethical and technical issues and solutions, as well as infrastructure needs to facilitate collaborative educational discourse research.