CAREER: Improving educators' trust in and effective uses of predictive learning analytics to support students

职业：提高教育工作者对预测学习分析的信任并有效利用它来支持学生

• 批准号: 2237593
• 负责人: Rene Kizilcec
• 金额: $ 80.76万
• 依托单位: Cornell University
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-04-01 至 2028-03-31
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2237593&HistoricalAwards=false
• 关键词: CAREER; Improving; educators; trust; effective

Predictive learning analytics (PLA) that have a focus on identifying students at risk of failing are gaining traction with leaders at all levels of education. The effective adoption and use of PLA in the US education system can promote educational attainment, STEM workforce development, and national development by supporting lower-resourced educational institutions and members of underserved communities. Prior research has focused on enhancing the technical implementation of these AI-based systems, but studies of why deployments of existing technologies have failed identify issues that are not technical but social, psychological, or cultural in nature. For example, educators’ trust in and effective use of PLA are instrumental for realizing their potential benefits, motivating this work to study how changes in the framing, level of transparency, and training can improve educators’ use of PLA. The project will involve 3,600 US educators across several large-scale studies and advance an understanding of what influences educators’ trust and effective use of PLA, as well as AI-based education technology more broadly. These insights will guide the development of an evidence-based curriculum about PLA for educators to foster awareness, trust, and effective use. The PLA training materials will be made available online and via posts on social media channels. This project develops concrete and scalable interventions to help design technologies that affect the academic progress of learners of all ages.Building on the Technology Acceptance Model and Academic Resistance Models, the project will investigate how educators respond to procedural justice framings and algorithmic transparency for AI-based education technology, especially during expectancy violation and high levels of uncertainty. Three studies will be conducted as online randomized controlled trials, replicated for robustness, that present educators with a simulated PLA to assess their perceptions, attitudes, and behavioral intentions. How different presentations of PLA influence educators’ usage intentions will be investigated by using an online noise audit, which quantifies how much the same information about students leads educators to the same conclusions about how to intervene. The cumulative insights of the project will be applied in a field experiment on a university campus to examine if evidence-based improvements to an existing at-risk identification process can encourage faculty to reach out to students and better support them. The project will contribute to significant advances in our causal understanding of ways to foster all educators’ trust and effective use of a learning analytics system. The award is funded in part by the EDU Core Research (ECR) program. The ECR program emphasizes fundamental STEM education research that generates foundational knowledge in the field. Investments are made in critical areas that are essential, broad and enduring: STEM learning and STEM learning environments, broadening participation in STEM, and STEM workforce development. This project is also funded by the Innovative Technology Experiences for Students and Teachers (ITEST) program, which supports projects that build understandings of practices, program elements, contexts and processes contributing to increasing students' knowledge and interest in science, technology, engineering, and mathematics (STEM) and information and communication technology (ICT) careers.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.

专注于识别有失败风险的学生的预测学习分析（PLA）正在与各级教育的领导者受到关注。在美国教育系统中，有效采用和使用PLA可以通过支持低资源的教育机构和服务不足社区的成员来促进教育成就，STEM劳动力发展和国家发展。先前的研究重点是增强这些基于AI的系统的技术实施，但研究了为什么现有技术的部署失败了，这些问题识别出不是技术，社会，心理或文化本质上的问题。例如，教育者对PLA的信任和有效使用有助于实现其潜在的好处，激发这项工作，以研究框架，透明度和培训水平的变化如何可以改善教育者对PLA的使用。该项目将在几项大型研究中涉及3,600名美国教育工作者，并促进对教育者的信任和有效使用PLA以及基于AI的教育技术的了解。这些见解将指导开发有关教育工作者的有关PLA的基于证据的课程，以促进意识，信任和有效使用。 PLA培训材料将在线提供，并通过社交媒体渠道上的帖子提供。该项目开发了具体和可扩展的干预措施，以帮助设计影响各个年龄段学习者的学术进步的设计技术。建立技术接受模型和学术抵抗模型，该项目将调查教育工作者如何应对基于AI的教育技术的程序性司法框架和算法的透明度，尤其是在预期和高水平的不良斗争期间。三项研究将作为在线随机对照试验进行的，以鲁棒性为复制，这些试验以鲁棒性复制，向教育者提供模拟的PLA，以评估他们的看法，参加和行为意图。通过在线噪声审核将如何研究PLA的不同演示文稿影响教育工作者的使用意图，该噪声量量化了有关学生的相同信息，导致教育工作者得出有关如何进行干预的相同结论。该项目的累积见解将在大学校园的实地实验中应用，以检查是否基于证据的高风险身份识别过程的改进可以鼓励教师与学生联系并更好地支持他们。该项目将有助于我们对培养所有教育者信任和有效利用学习分析系统的方式的灾难性理解的重大进步。该奖项由EDU Core Research（ECR）计划部分资助。 ECR计划强调了基本的STEM教育研究，该研究在该领域产生了基础知识。投资是在重要，广泛和结束的关键领域进行的：STEM学习和STEM学习环境，扩大参与STEM以及STEM劳动力的发展。该项目还由针对学生和教师（ITEST）计划的创新技术经验资助，该计划支持对实践，计划要素，环境，环境和过程的理解，从而有助于增加学生对科学，技术，工程和数学和数学（STEM）的知识和兴趣的知识和兴趣，并通过对ICT的授权（ICT）授予的授权来表示，并反映了ICTIONT INFRACTION INFRAI​​CTION INFERPORITARINAL。和更广泛的影响审查标准。