BIGDATA: EAGER: Catalyzing Research in Multimodal Learning Analytics

数据科学技术已经给许多学术领域带来了革命性的变化，并在商业领域带来了巨大的收益。到目前为止，它们在解决美国教育系统中的关键问题方面一直没有得到充分利用，特别是在了解科学、技术、工程和数学(STEM)学习和学习环境、扩大STEM的参与以及增加传统上STEM服务不足的学生的留住方面。教育和人力资源局通过推进大数据科学与工程(BigData)计划的基础和应用的关键技术和技术，目标是促进旨在理解和解决这些关键问题的基础研究，并促进数据科学在教育研究中的使用。随着越来越多的开放式学习环境被学校采用，了解它们如何影响STEM的学习、动机和参与度是至关重要的。教育研究中最广泛使用的方法不足以解决这些问题，因为它们没有解决从这些环境中提供的数据的规模和复杂性。目前在学习科学和教育研究中分析这些类型数据的标准做法是用音频或视频记录学生在这些空间中的活动，创建定性编码方案，并手动对数据进行编码。这是劳动密集型的，容易受到个人判断和错误的影响。它还倾向于导致研究不可复制或可扩展。例如，如果每个研究合作或发展规划技能等重要教育领域的研究人员在他们的工作中使用他或她自己的编码框架，就很难对这些研究的结果进行分组，也很难理解更大的图景。此外，一个研究小组通常不可能通过尝试使用另一个小组的编码框架来复制另一个研究小组发现的结果。这项探索性研究的早期概念资助(AGIRE)将通过将计算机科学、数据科学和教育研究方面的专家聚集在一起，开发研究这些不太可能存在相同问题的环境的新方法，从而促进对前景光明的新技术环境如何影响这些结果的理解。通过使用来自新的数据捕获方法的数据，例如与制造者空间中的对象的交互日志或新的数据挖掘技术来分析来自音频或视频记录的数据，首席调查人员寻求极大地提高该领域了解人们在这些环境中学习的能力。首席调查人员建议将数据分析、计算机科学和教育研究方面的专家聚集在一起，开发新的方法来追求多模式学习分析(MLA)。MLA开启了探索学习环境的大门，无论是教室还是设计工作室，这些以前都很难调查。新型传感器和数据挖掘技术使捕获通常在这些空间的活动中丢失的过程数据成为可能。督导人员建议透过一连串的工作坊来达致这个目标。第一个将定义方向，并将潜在工具映射到它们可以用来测量的重要结构。中间研讨会构成了工具开发和改进的一系列迭代周期。最后的Hack-a-thon研讨会将包括参与者编写将向社区开放的工具的原型和完整模型。

Data science techniques have revolutionized many academic fields and led to terrific gains in the commercial sector. They have to date been underutilized in solving critical problems in the US educational system, particularly in understanding Science, Technology, Engineering and Mathematics (STEM) learning and learning environments, broadening participation in STEM, and increasing retention for students traditionally underserved in STEM. The goals of the Directorate for Education and Human Resources through the Critical Techniques and Technologies for Advancing Foundations and Applications of Big Data Science & Engineering (BIGDATA) program are to advance fundamental research aimed at understanding and solving these critical problems, and to catalyze the use of data science in Education Research. As more open-ended learning environments are being employed in schools, it is critical to understand how they affect learning, motivation and engagement in STEM. The most widely used methods in educational research are inadequate for addressing these questions because they do not address the scale and complexity of the data provided from these environments. The current standard practice in learning science and education research for analyzing these types of data is to record student activity in these spaces on audio or video, create qualitative coding schemes, and code the data by hand. This is labor intensive and prone to personal judgment and error. It also tends to result in research that is not replicable or scalable. For example, if each researcher studying important educational areas like collaboration or developing planning skills uses his or her own coding framework in their work, it makes it difficult to group the results of these studies and understand the bigger picture. In addition, it is often impossible for one research group to reproduce the results another research group found by trying to use the other group's coding framework. This Early Concept Grant for Exploratory Research (EAGER) will advance the understanding of how promising new technology environments affect these outcomes by bringing together experts in computer science, data science and education research to develop new methods of studying these environments that are not likely to have the same problems. By using data from new methods of data capture such as logs of interaction with the objects in a maker space or new data mining techniques to analyze data from audio or video recordings, the Principal Investigators seek to greatly increase the field's ability to learn about what people are learning in these environments.The Principal Investigators propose to bring together experts in data analysis, computer science, and educational research to develop new ways to pursue multimodal learning analytics (MLA). MLA opens the door to exploring learning environments, whether classrooms or design studios, that have been difficult to investigate before. New types of sensors and data mining techniques make it possible to capture the process data that is usually lost in the activities in these spaces. The PIs propose to achieve this through a series of workshops. The first will define directions and map potential tools to important constructs they can be used to measure. The middle workshops constitute a series of iterative cycles of tool development and refinement. The final hack-a-thon workshop will involve participants coding prototypes and full models of tools that will be openly available to the community.