Collaborative Research: Using Adaptive Lessons to Enhance Motivation, Cognitive Engagement, And Achievement Through Equitable Classroom Preparation

该项目旨在通过响应推进个性化学习的巨大挑战的号召，为国家利益服务（美国国家工程院）。该研究与开发（R&amp；D）项目将开展全面的概念复制和适应工作，以检查在混合式主动学习课堂中，以课前适应性学习平台（APL）课程/学习模块形式存在的先验知识与学生情感和认知结果的关联程度。在混合式主动学习课堂中，学生应该在课前做好准备，例如，通过视频和在线评估复习之前的知识。在二年级和三年级教授的五门工程核心课程将作为测试适应性学习的课堂设置。该测试将通过比较通过学习管理系统（LMS）提供的“一刀切”的课前活动与通过自适应学习平台（ALP）提供的适应性灵活的课前课程来完成。课程包括统计检验与回归、线性电路与系统、流体系统、工程流体力学和计算方法。一套已发表的评估，包括概念清单，将被用来比较学生在LMS和ALP环境中的认知和情感结果。该研发项目将用于(1)开发、改进和部署三个机构的五门课程的ALP课程、比较LMS内容以及课内和课后练习；(2)比较有适应性学习（实验）和没有适应性学习（控制）的混合课堂准备的认知结果（即概念、程序和高阶问题解决）和情感结果（认知参与和学习动机）；(3)分析ALP分析/指标，研究学生的学习行为（如课前准备时间、测验次数和提前完成次数）及其与结果的关系；(4)通过开放教育材料、期刊/会议文章、社交媒体、网站和教师研讨会交流发现和最佳实践。开发和研究工作将通过三所机构的工程和工程教育教师和研究人员的合作进行：南佛罗里达大学、中佛罗里达大学和匹兹堡大学。调查将重点关注先验知识（通过学生参与课前活动和不同水平的学生准备培养）与学生的认知和情感结果（如成绩、认知参与和学习动机）之间的作用和联系。定量和定性混合方法研究将由学生背景因素和学生人口统计数据（例如，GPA、性别、种族、年龄、佩尔助学金状态、转学状态）、现有的、已发表的和已测试的评估工具以及使用人工智能增强技术进行适应性学习的理论和方法（RealizeIT）构成。参数和非参数统计方法/方法以及演绎和归纳方法/框架将指导数据收集，分析和解释。NSF IUSE: EDU项目支持研究和开发项目，以提高所有学生STEM教育的有效性。通过参与学生学习轨道，该计划支持创建，探索和实施有前途的实践和工具。该奖项反映了美国国家科学基金会的法定使命，并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，被认为值得支持。

This project aims to serve the national interest by responding to the call to address the grand challenge of advancing personalized learning (National Academy of Engineering). This research and development (R&D) project will embark on a comprehensive conceptual replication and adaption effort to examine the degree to which prior knowledge, in the form of pre-class adaptive learning platform (APL) lessons/learning modules, is associated with student affective and cognitive outcomes in blended active learning classrooms. In a blended active learning classroom, students are expected to prepare before class, for example, by reviewing prior knowledge using videos and online assessments. Five engineering core courses taught at the sophomore and junior levels will serve as classroom settings for testing adaptive learning. This testing will be done by comparing "one-size-fits-all" pre-class activities delivered via the Learning Management System (LMS) with adaptive and flexible pre-class lessons delivered via an adaptive learning platform (ALP). Courses include Statistical Testing and Regression, Linear Circuits and Systems, Fluid Systems, Engineering Fluid Mechanics, and Computational Methods. A set of published assessments, including concept inventories, will be administered to compare students' cognitive and affective outcomes in the LMS and ALP environments. This R&D project will be used to (1) develop, improve, and deploy ALP lessons as well as the comparative LMS content in addition to in-class and post-class exercises for five courses at three institutions; (2) compare cognitive outcomes (i.e., conceptual, procedural, and higher-order problem-solving) and affective outcomes (cognitive engagement and academic motivation) with adaptive learning (experimental) vs. without adaptive learning (control) for blended classroom preparation; (3) analyze ALP analytics/metrics to study student learning behaviors (such as time spent on pre-class preparation, number of quiz attempts, and early completion counts) and their relationship to the outcomes; and (4) communicate findings and best practices via open educational materials, journal/conference articles, social media, websites, and faculty workshops. The development and research effort will be conducted through a collaboration of engineering and engineering education faculty and researchers at three institutions: the University of South Florida, the University of Central Florida, and the University of Pittsburgh. The investigation will focus on the role and association of prior knowledge (as fostered by student participation in pre-class activities and differential levels of student preparedness) with students' cognitive and affective outcomes, such as achievement, cognitive engagement, and academic motivation. The quantitative and qualitative mixed methods study will be framed by student background factors and student demographics (e.g., GPA, gender, ethnicity, age, Pell Grant status, transfer status), existing, published, and tested assessment instruments, and theories of and approaches to adaptive learning with AI-enhanced technology (RealizeIT). Parametric and non-parametric statistical approaches/methods and deductive and inductive approaches/framing will guide the data collection, analysis, and interpretation. The NSF IUSE: EDU Program supports research and development projects to improve the effectiveness of STEM education for all students. Through the Engaged Student Learning track, the program supports creating, exploring, and implementing promising practices and tools.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.