CISE-MSI: DP: IIS-III: ACOSUS: An AI-driven COunseling System for Underrepresented Transfer Students

该奖项的全部或部分资金来自《2021年美国救援计划法案》(公法117-2)。2021年的统计数据显示，从事计算机工作的人中，只有15%是黑人和西班牙裔，25%是女性，而32.56%的大学生是代表不足的少数族裔。在与计算相关的领域，迫切需要高度多样化的劳动力。社区学院和四年制大学之间的转学途径是劳动力多样化的一个关键因素。事实上，这些机构中的许多都面临着为转学学生提供联合建议的挑战，因为从他们决定转学到转学后毕业的道路存在不确定性，特别是那些来自计算机专业弱势少数群体或代表性不足的群体的学生。利用信息系统帮助这些学生提高技能，转学到大学，并在就业市场取得成功，这是高等教育的一个关键但具有挑战性的目标。该项目的总体目标是(1)调查学生在转学决策过程、在校表现和就业安置过程中遇到的挑战，(2)设计一个创新的人工智能驱动的学生咨询系统，为计算机等专业的未被充分代表的转学学生提供个性化的准备评估和建议。该项目旨在全面了解个人、学业和行为因素如何影响未被充分代表的学生在追求教育和职业决策的过程中。它还探讨了影响他们的决定和追求目标的努力的环境因素，如社会规范和社交媒体。利用这些信息，该项目设计和评估了一个人工智能驱动的咨询系统，该系统整合了针对代表性不足的学生的个人、学术、行为和环境因素，不仅评估他们为提升技能转移和就业市场做好了准备，还提供了改进建议和资源。该系统在设计中使用了自然语言处理算法、深度神经网络以及其他人工智能方法。它还使用数据管理技术来消除目前人工智能驱动的系统中普遍存在的种族和性别偏见。这一奖项反映了NSF的法定使命，并通过使用基金会的智力优点和更广泛的影响审查标准进行评估，被认为值得支持。

This award is funded in whole or in part under the American Rescue Plan Act of 2021 (Public Law 117-2).Statistics in 2021 show that only 15% of workers in computing occupations are Black and Hispanic, and 25% are female, whereas 32.56% of college students are underrepresented minorities. There is a dire need for a highly diversified workforce in computing-related fields. A crucial contributor to a diverse workforce is the transfer pathways between community colleges and 4-year universities. In fact, many of these institutions have challenges co-advising transfer students due to the uncertainty surrounding the path from their decision to transfer to post-transfer graduation, particularly those who are from disadvantaged minority or underrepresented groups in computing majors. The use of information systems to assist these students in their upskilling transfer to universities and job market success is a critical but challenging objective of higher education. The overarching goal of this project is to (1) investigate the challenges experienced by students in their transfer decision-making process, school performance, and job placement, and (2) design an innovative AI-driven student advising system that provides personalized readiness assessment and suggestions to underrepresented transfer students in computing majors, among others.The project aims to gain a comprehensive understanding on how personal, academic, and behavioral factors influence underrepresented students in their pursuit of education and career decisions. It also explores environmental factors like social norms and social media that impact their decision and goal-pursuing endeavors. Using this information, the project designs and evaluates an AI-driven advising system that integrates personal, academic, behavioral, and environmental factors specific to underrepresented students to not only assess their preparedness for upskilling transfer and the job market, but provide improvement suggestions and resources as well. The system uses natural language processing algorithms, deep neural networks, along with other AI approaches in its design. It also employs data curation techniques to eliminate the racial and gender bias that is prevalent in current AI-driven systems.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.