SBIR Phase I: A Student Learning Dashboard

这个小企业创新研究（SBIR）第一阶段项目的更广泛/商业影响是提高高等教育的保留率和提高毕业率。目前，美国大学的平均辍学率为40%。此外，得不到充分服务的科学、技术、工程和数学（STEM）学生更有可能没有学位就离开学校。由于COVID-19大流行，财务不安全和心理健康挑战的增加对学生的学习产生了负面影响。该项目旨在开发一个学生学习仪表板平台，通过提供有针对性、个性化和实时可操作的帮助，在学生的高等教育学习过程中充当副驾驶。该解决方案整体地识别每个学生独特的学习动机挑战（例如，科目难度，与职业目标的相关性，社会和经济约束等），并提供克服障碍的具体建议。指导学生学习如何根据自己的情况更有效地学习，培养一种成长的心态、勇气和能动性，帮助他们成为成功的终身学习者。该应用程序还显著提高了高等教育的多样性、公平性和包容性，特别是在STEM领域，从而提高了有效的劳动力培训。这个小企业创新研究（SBIR）第一阶段项目使用机器学习来了解每个学生独特的学习挑战，绘制障碍如何影响学习动机，并影响课程参与度。机器学习被用于分析定性和定量的学习动机和行为数据，以识别差距，以便在学生仍在学习过程中提供实时、有针对性的相关指导，而不是等到可能为时已晚的时候进行干预。该项目提供描述性、预测性和说明性的建议，以模拟一对一、个性化的大规模、低成本建议。当学生表现出学业和非学业上的挣扎影响他们的学习心理状态时，这项技术还可以作为一个早期检测系统。当需要人工干预时，可以通知教师、学术建议和/或相关的校园学生支持服务。这个项目可以被任何教育机构或私人公司使用，提供面对面、翻转/混合、远程、同步或异步教学格式。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。

The broader/commercial impact of this Small Business Innovation Research (SBIR) Phase I project is in improving retention in higher education and increasing graduation rates. Currently, the average U.S. college dropout rate is 40%. Moreover, underserved Science, Technology, Engineering and Mathematics (STEM) student populations are more likely to leave school without a degree. Due to the COVID-19 pandemic, increased financial insecurity and mental health challenges have negatively impacted student learning. This project aims to develop a student learning dashboard platform that acts as a co-pilot during students' higher education learning journey by delivering targeted, personalized, and real-time actionable assistance. The solution holistically identifies each student's unique learning motivation challenges (e.g., subject difficulty, relevance to career goals, social and economic constraints, etc.) and provides specific recommendations to overcome barriers. Coaching students to learn how to learn more effectively based on their own context fosters a growth mindset, grit, and agency to help them become successful lifelong learners. The application also significantly improves diversity, equity, and inclusion in higher education, especially in STEM, and thus increases effective workforce training. This Small Business Innovation Research (SBIR) Phase I project uses machine learning to understand each student's unique learning challenges, map how barriers affect learning motivation, and influences coursework engagement. Machine learning is applied to analyze qualitative and quantitative learning motivation and behavior data to identify gaps so real-time, targeted, and relevant guidance can be delivered while the students are still progressing through the courses rather than waiting until it might be too late for intervention. This project provides descriptive, predictive, and prescriptive recommendations to simulate one-on-one, personalized advising at scale and at a lower cost. The technology also acts as an early detection system when students show the first sign of academic and non-academic struggles affecting their mental state of readiness to learn. When in-person human intervention is required, instructors, academic advising, and/or relevant on-campus student support services can be alerted. This project can be used by any educational institution or private company providing in-person, flipped/hybrid, remote, synchronous, or asynchronous instruction formats.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.