REU Site: Undergraduate Research in Educational Data Mining

REU 网站：教育数据挖掘本科生研究

• 批准号: 1757064
• 负责人: Huzefa Rangwala
• 金额: $ 36万
• 依托单位: George Mason University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2018
• 资助国家: 美国
• 起止时间: 2018-03-15 至 2022-02-28
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1757064&HistoricalAwards=false
• 关键词: REU; Site; Undergraduate; Research; Educational

The Research Experiences for Undergraduates (REU) Site at George Mason University focuses on data science and engineering research applied to solving grand challenges within the educational domain. Each summer for ten weeks, ten undergraduate students will participate in training and research activities, gaining skills pertaining to the typical lifecycle of a data analytics project. This program will focus on "learning by doing" which will illustrate to students the creativity and technical skills involved in solving complex real world problems. The project is led by a team of experienced faculty who will mentor the participating researchers through a number of professional development activities that prepare them for future careers as professionals in the field of data science, which has been identified as priority areas for the workforce of the future. This program will engage and recruit underrepresented minorities and women to pursue multi-disciplinary careers that transcend computer science, engineering and educational sciences. Careful student-student and student-mentor(s) pairings, as well as opportunities for developing organically-formed partnerships, will foster an inclusive academic culture. Given the trans-disciplinary focus of this program, there will a direct impact in increasing the awareness of data analytics and visualization techniques, and their potential impacts in a broad range of domains. The educational domain is useful in that it is a common denominator: most students have direct experience with education processes through primary, secondary, and postsecondary schools. The primary goal of this interdisciplinary REU Site program is to expose undergraduate students to advanced topics in analytics, data mining, and visualization techniques as applied to data from the education domain. Students will participate in projects with the central theme of improving instructional technology design, enhancing academic curricula and modeling learning experiences. From an analytical methodology standpoint, projects will investigate approaches to model the dynamic knowledge state of a student enrolled in a sequence of courses within a sequential academic program. Projects will model the learning behavior of younger students in informal settings by analyzing the server logs of the Scratch framework or Online Engineering Communities. Projects will also model the learning habits of practitioners while interacting with online programming environments. This focus on education-centered analysis will provide the participating undergraduate students a deeper understanding of both general data mining techniques and a broader taste for educational design. The program will have an immediate impact on a diverse group of students by introducing them to the nuances of interdisciplinary research process, sparking an interest in computing and learning sciences, and more importantly fostering lifelong professional relationships with mentors and peers. More information about this project and additional resources will be available at http://www.cs.gmu.edu/reuThis 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.

乔治梅森大学的本科生研究经验（REU）网站专注于应用于解决教育领域重大挑战的数据科学和工程研究。每年夏天，十名本科生将参加为期十周的培训和研究活动，获得与数据分析项目的典型生命周期相关的技能。该计划将侧重于“边做边学”，这将向学生展示解决复杂的真实的世界问题所涉及的创造力和技术技能。该项目由经验丰富的教师团队领导，他们将通过一些专业发展活动指导参与研究人员，为他们未来的职业生涯做好准备，成为数据科学领域的专业人士，这已被确定为未来劳动力的优先领域。 该计划将吸引和招募代表性不足的少数民族和妇女，以追求超越计算机科学，工程和教育科学的多学科职业。认真的学生和学生导师（S）配对，以及发展有机形成的伙伴关系的机会，将促进包容性的学术文化。 鉴于该计划的跨学科重点，将直接影响提高对数据分析和可视化技术的认识，以及它们在广泛领域的潜在影响。教育领域是有用的，因为它是一个共同点：大多数学生有直接的经验，通过小学，中学和中学后的教育过程。这个跨学科的REU网站计划的主要目标是让本科生接触到应用于教育领域数据的分析，数据挖掘和可视化技术的高级主题。学生将参加以改进教学技术设计，加强学术课程和建模学习经验为中心主题的项目。 从分析方法的角度来看，项目将调查方法来模拟学生的动态知识状态，在一个连续的学术课程的课程序列注册。项目将通过分析Scratch框架或在线工程社区的服务器日志来模拟年轻学生在非正式环境中的学习行为。项目还将模拟从业者的学习习惯，同时与在线编程环境进行交互。 这种以教育为中心的分析将为参与的本科生提供对一般数据挖掘技术和教育设计的更广泛品味的更深入理解。该计划将通过向学生介绍跨学科研究过程的细微差别，引发对计算和学习科学的兴趣，更重要的是培养与导师和同行的终身专业关系，对不同群体的学生产生直接影响。有关该项目的更多信息和额外资源将在www.example.com上提供http://www.cs.gmu.edu/reuThis奖项反映了NSF的法定使命，并被认为值得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来支持。

项目成果

Editable AI: Mixed Human-AI Authoring of Code Patterns

• DOI: 10.1109/vlhcc.2019.8818871
• 发表时间: 2019-10
• 期刊: 2019 IEEE Symposium on Visual Languages and Human-Centric Computing (VL/HCC)
• 作者: Kartik Chugh;Andrea Y. Solis;Thomas D. Latoza

Revisiting the Effects of Leakage on Dependency Parsing

重新审视泄漏对依存句法分析的影响

• 发表时间: 2022
• 期刊: Transactions of the Association for Computational Linguistics
• 影响因子: 10.9
• 作者: Krasner, Nathaniel;Wanner, Miriam;Anastasopoulos, Antonios
• 通讯作者: Anastasopoulos, Antonios

Using Online Textbook and In-Class Poll Data to Predict In-Class Performance.

使用在线教科书和课堂民意调查数据来预测课堂表现。

• 发表时间: 2020
• 期刊: Educational Data Mining
• 作者: Hunt-Isaak, Noah;Cherniavsky, Peter;Snyder, Mark;Rangwala, Huzefa
• 通讯作者: Rangwala, Huzefa