SBIR Phase I: A Digital Platform That Engages Elementary Aged Girls In STEM Through Personalized Informal Learning

The broader impact of this Small Business Innovation Research (SBIR) Phase I project is ultimately to increase the representation of women in Science, Technology, Engineering, and Math (STEM) employment areas, enabling the US to meet the increasing demand for STEM workers and maintain competitiveness in the global innovation community. Factors promoting underrepresentation of girls and women in STEM often take effect early in education and extend beyond traditional classrooms settings; this solution specifically addresses the support needed by parents in order to facilitate STEM informal learning in a way that is particularly engaging for their young daughters. This proposed project, based on evidence-based research in learning in informal environments, will deliver monthly personalized informal learning plans to enable parents to catalyze positive STEM experiences for girls early in their learning journeys so that they are more likely to embrace STEM careers and better positioned to secure them in the future. This Small Business Innovation Research (SBIR) Phase I project will transform the way young girls perceive and engage in STEM career exploration by providing a progressive playlist of STEM informal learning experiences personalized to their unique interests. This is accomplished through a novel artificial intelligence (AI) driven recommender system that learns from user preferences and attributes to recommend content and learning experiences, which are meant to increase STEM confidence and interest for young girls as well as inspire their curiosity. Parents can opt to provide immediate feedback on the recommended plan that further tunes the plan to their child’s needs or swap selections with secondary recommendations. The proposed project’s objectives are to develop and test algorithmic model for sequenced recommendations, design and build the prototype application, and conduct research to determine that personalized recommendation sequences deepen and/or expand STEM knowledge and interests. To guide the development, efficacy of the recommender will be assessed by comparing results from conducting studies using human recommendations with results using the AI recommender. Once the algorithmic model is established, pre and post assessments will be conducted to assess impact of the intervention on engagement and curiosity with STEM, thereby contributing to an increase in knowledge in the field as well as a commercially applicable and timely marketplace product. 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.