SBIR Phase II: A novel method to scaling mentoring and career development in Institutes of Higher Education

The broader/commercial impact of this SBIR Phase II project is to improve academic and career outcomes for first-generation and underrepresented students in higher education through an Artificial Intelligence (AI)-driven Software-as-a-Service (SaaS) platform which harnesses individual learning, self-reflection, and automation to make every course a high-impact learning experience. By integrating competency-based learning, self-reflection, and near-peer mentoring, the project aims to develop crucial social capital alongside essential skills and competencies, maintaining a human element in conjunction with technology.

The technology creates comprehensive learner profiles and applies natural language processing to generate personalized recommendations for career guidance and academic navigation. This innovation addresses the critical shortage of counseling resources in public colleges, where student-to-counselor ratios can reach 1:1,800. The project applies natural language processing (NLP) techniques to student learning profiles and competency to tap into a unique experiential learning recommendation engine for career guidance and academic navigation in higher education classrooms.

This innovation aims to expand the toolkits of each faculty member's high-impact practice to their course learning strategies to enhance classroom learning strategies.

This Small Business Innovation Research (SBIR) Phase II project aims to enhance academic and career outcomes for students by leveraging natural language processing (NLP) and machine learning (ML) algorithms. The research builds upon a proprietary data representation model developed in Phase I to analyze student competencies, interests, and self-efficacy.

The project's objectives are twofold: 1) Integrate diverse pedagogical philosophies into a unified system for curriculum modularization, student work assessment, and mentoring evaluation; 2) Develop a conversational AI engine utilizing Large Language Models (LLMs) to support self-regulated learning reflection and career exploration. The research methodology involves applying NLP techniques to student learning profiles and competency data to identify patterns in self-efficacy and learning strategies.

The proposed approach will then generate personalized recommendations for career guidance and academic navigation. Anticipated technical results include a robust AI-driven system capable of analyzing student learning trajectories, providing tailored mentorship matches, and suggesting career-connected strategies. This research aims to bridge the gap between academic learning and career readiness, potentially transforming how students engage with their educational journey and future occupational identities.

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.