DataShop: A Data Repository and Analysis Service for the Learning Science Community (Interactive Event)
DataShop: A Data Repository and Analysis Service for the Learning Science Community (Interactive Event)
复制标题
DataShop：面向学习科学社区的数据存储库和分析服务（互动活动）
DOI：
10.1007/978-3-642-21869-9_129
复制
发表时间：
2011
期刊：
影响因子：
--
通讯作者：
Duncan Spencer
中科院分区：
文献类型：
--
作者：
John C. Stamper;K. Koedinger;R. Baker;A. Skogsholm;Brett Leber;Sandy Demi;Shawnwen Yu;Duncan Spencer
匹兹堡学习科学中心的DataShop是一个开放的数据存储库和一组相关的可视化和分析工具。DataShop拥有来自数千名学生的数据，这些数据来自与在线课程材料和智能辅导系统的互动。这些数据是细粒度的，大约每20秒记录一次学生的行为，并且是纵向的，跨越学期或一年的课程。截至2011年4月8日，存储了超过270个数据集，包括超过5800万个学生操作和超过165，000个学生小时的数据。大多数学生的行为都是“编码”的，这意味着他们不仅被分为正确或不正确的，但根据执行该行动所需的假设能力或知识组成部分进行分类。DataShop为存储库用户提供了一个中心枢纽，以满足长期的数据管理需求。DataShop还具有许多促进数据分析的功能，包括数据模式，允许研究人员将数据导入DataShop或从存储库导出数据，以执行额外的分析。DataShop提供了许多在线分析工具来执行功能，例如可视化学生表现和分析学习曲线。研究人员可以导出认知模型，进行更改，并上传更改后的模型以供进一步分析。DataShop中添加的一个新特性是一个易于使用的API，用于使用Web服务访问存储库。这些Web服务允许开发人员识别存储库中的数据集，并在事务或学生步骤级别直接从中导出数据。在不久的将来，开发人员将能够使用我们的自定义字段Web服务将新字段添加回存储库。
The Pittsburgh Science of Learning Center’s DataShop is an open data repository and set of associated visualization and analysis tools. DataShop has data from thousands of students deriving from interactions with on-line course materials and intelligent tutoring systems. The data is fine-grained, with student actions recorded roughly every 20 seconds, and it is longitudinal, spanning semester or yearlong courses. As of April 8, 2011, over 270 datasets are stored including over 58 million student actions and over 165,000 student hours of data. Most student actions are “coded” meaning they are not only graded as correct or incorrect, but are categorized in terms of the hypothesized competencies or knowledge components needed to perform that action. DataShop provides repository users a central hub to satisfy long term data management needs. DataShop also has a number of features to facilitate data analysis including a data schema that allows researchers to import data into DataShop or export data from the repository in order to perform additional analysis. DataShop offers a number of online analysis tools to perform functions, such as visualizing student performance and analyzing learning curves. Researchers can export cognitive models, make changes, and upload the changed model for further analysis. One new feature that has been added to DataShop is an easy-to-use API for using web services to access the repository. These web services allow developers to identify data sets in the repository and directly export data from them at the transaction or student step level. In the near future, developers will be able to add new fields back into the repository with the use of our web services for custom fields.