Sbir phase i: sown to grow - measuring growth in trusting relationships between students and educators with natural language processing and machine learning technologies

This $275,000 SBIR Phase I award from the National Science Foundation's (NSF) Technology, Innovation, and Partnerships (CFDA 47.084) program supports research and development by Sown To Grow, Inc., a for-profit small business, to develop an innovative technology that measures the strength of student-teacher relationships at scale. The project aims to create new frameworks for defining trusting relationships based on the depth of student reflections, teacher responses, and how those responses change over time. The technology will leverage advanced natural language processing (NLP) and machine learning (ML) techniques to model these frameworks and generate a student-teacher relationship trust metric. This metric will help schools and districts across the country better understand the emotional health and relationship strength in their schools, with the goal of improving student well-being, reducing absenteeism, and addressing teacher burnout. Sown To Grow, Inc. will serve as the sole prime recipient for this 12-month project.

Abstract

The broader/commercial impact of this small business innovation research (sbir) phase i project seeks to help educators to develop deeper relationships with their students, assist schools in identifying students who lack strong relationships and need additional support, and help school districts understand the emotional health and relationship strength of their schools. Student emotional well-being, student absenteeism, and teacher burnout are some of the most pressing problems facing k-12 education today. A significant body of research shows that positive student-teacher relationships help students adjust to school, contribute to social skill development, promote academic performance and resiliency, decrease absenteeism, and foster engagement. Schools struggle with relationship building at scale - IT takes time to form connections, not all students are willing to open up, and teachers need help and training on understanding and responding to the varied experiences and needs of their students. This project, if successful, will help schools address these challenges at scale. Additionally, the data from this project will help teachers contribute to learning science and behavioral health research, while providing a blueprint to the education technology industry on how to implement advanced technology in an ethical and transparent manner that augments, rather than replaces, existing education structures and systems. This project builds an innovative technology that will understand and measure the strength of the student-teacher relationships at scale. The technology will develop new frameworks for defining trusting relationships based on the depth of student reflections, teacher responses, and how responses change and grow week over week. Advanced natural language processing (NLP) and machine learning (ML) techniques will model these frameworks based on real student-teacher interactions. NLP typically focuses on using models to understand text inputs and predict/generate responses. Through this project, the team seeks to use new NLP/ML techniques to understand and assess the interactions and levels of trust between individuals. The NLP/ML models will analyze the depth of student reflections and interpret the nature of the teacher responses separately. The output of these two models will then be combined to understand the strength of student-teacher relationship by creating a student-teacher relationship trust metric. This metric will help understand student-teacher relationships at scale across schools and districts all over the country. 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.- subawards are not planned for this award.