Dr. Wei Ai of the UMD INFO College is a co-PI on this groundbreaking project
Seattle, WA—An innovative new project that leverages machine learning to assess mathematics lesson plan quality in the middle grades has been selected by the National Science Foundation (NSF) to receive a $1.5 million grant. Through this project, a cross-university research team led by principal investigator Dr. Min Sun of the University of Washington College of Education will identify ways to measure the quality of large quantities of open-source mathematics lesson plans using an integration of cutting-edge machine learning techniques, knowledge of effective mathematics education and human feedback.
As online instructional materials continue to proliferate, schools and educators are increasingly relying on them for lesson planning, underscoring the need to evaluate the quality of these materials. Planning and selecting instructional materials are among the most complex and important components of mathematics teaching, and this project aims to make it easier for middle school mathematics teachers to design lesson plans that are effective and support positive learning outcomes for students.
From left to right: Dr. Min Sun, UW College of Education; Dr. Lorraine Males, University of Nebraska – Lincoln; Dr. Melissa Boston, Duquesne University School of Education; Dr. Wei Ai, University of Maryland College of Information Studies; and Dr. Jing Liu, University of Maryland College of Education.
“[W]e are addressing equity issues because junior teachers spend more time on lesson planning, as do teachers serving historically marginalized students and communities.” -Dr. Min Sun, UW College of Education
“This project will democratize access to quality, inclusive and tailored learning materials that benefit students and support their teachers’ planning processes,” Dr. Sun shares.
“Beyond scientific contributions, we are addressing equity issues because junior teachers spend more time on lesson planning, as do teachers serving historically marginalized students and communities,” she elaborates. “It’s critical that teachers’ lesson plans, especially in mathematics instruction, effectively supports students with a wide range of academic performance levels, language and cultural backgrounds.”
Teachers are increasingly turning to online platforms and social media sites to supplement their district curricula, either for content enrichment or to make lessons more interactive and culturally relevant. Research reveals that a vast majority of teachers use search engines like Google and platforms like TeachersPayTeachers and Pinterest to source lesson materials. With the rise of ChatGPT, a recent survey conducted by the Walton Family Foundation shows that 40% of teachers use ChatGPT on a weekly basis for tasks such as lesson planning and building background knowledge for lessons. This increasing shift towards digital resources is also supported by the burgeoning movement of Open Education Resources (OER) under the Creative Commons License. This movement is backed by state agencies, including in Washington state, prominent non-profit organizations and even district or university initiatives. Consequently, many school districts nationwide have chosen OER materials as their primary curricula. These shifts highlight the importance of developing a quality checker of online content to better support teachers and student learning outcomes.
“A big promise of AI is that it will help relieve teachers from many routine tasks, including lesson planning, so they can spend more time working with students.” -Dr. Jing Liu, University of Maryland College of Education
“Lesson planning is a critical yet not well-studied component of teaching,” says Dr. Jing Liu of the University of Maryland School of Education and a co-principal investigator of this project. “Despite their busy schedules, teachers spend a lot of time developing their lesson plans, but there is little guidance on how to evaluate and identify high-quality lesson plans. A big promise of AI is that it will help relieve teachers from many routine tasks, including lesson planning, so they can spend more time working with students.”
“Importantly, teachers’ input and voices are centered in this work throughout, so machine learning techniques are used in a very responsible manner,” Dr. Liu adds.
The use of machine learning to measure lesson plan quality holds transformative potential for the field of mathematics education. The team has chosen to focus on assessing the quality of online instructional materials intended for middle-grade math because this is the period when math content starts to become more complex.
“Students need to learn foundational math concepts and skills and build connections among them, to set themselves up for success in STEM learning in high school,” Dr. Sun explains. “In conjunction with the unique challenges adolescents face in terms of their physical and social-emotional development, middle school math becomes a fruitful subject and grade area for this project to focus on.”
The team will develop artificial intelligence- and machine learning-powered algorithms, in collaboration with human expert judgement, to check a lesson plan’s content rigor, engagingness of activities and inclusivity for students with language and special education needs. The algorithms and data practices can be used to develop effective and responsible AI products for teachers.
“As teachers increasingly turn to the Web for resources, our research is pivotal in addressing information overload and guiding them toward high-quality lesson plans.” -Dr. Wei Ai, University of Maryland College of Information Studies
“Our project combines the collective wisdom of educational experts with the power of machine learning in processing large quantities of data. As teachers increasingly turn to the Web for resources, our research is pivotal in addressing information overload and guiding them toward high-quality lesson plans. The recent rise of large foundational models (such as those used behind ChatGPT) only intensifies the urgency of this initiative, as it enables the machine learning community to develop their models using only the best in educational content,” says Dr. Wei Ai, co-principal investigator and faculty member at the University of Maryland College of Information Studies.
Findings from this project will be shared through the AmplifyLearn.AI Center website, which will launch in October 2023. Led by Dr. Sun, the center is a cross-institution collaboration that explores AI research in education, AI-powered EdTech product development and education data science training and outreach. Additionally, all educators will soon have open access to Colleague, a K-12 online lesson planning platform developed by a multidisciplinary team at the University of Washington led by Dr. Sun that hosts a comprehensive collection of vetted lesson plan materials. The Colleague platform will be launching beta testing this fall and educators and schools are encouraged to stay tuned for updates and opportunities to be part of this testing phase.
In addition to Drs. Ai and Liu, Dr. Sun’s co-principal investigators under the NSF grant include Dr. Lorraine Males of the University of Nebraska – Lincoln, College of Education and Dr. Melissa Boston of Duquesne University School of Education.
This project is supported by the NSF’s EDU Core Research (ECR) Program. The ECR program emphasizes fundamental STEM education research that generates foundational knowledge in the field. Investments are made in critical areas that are essential, broad and enduring: STEM learning and STEM learning environments; broadening participation in STEM; and STEM workforce development.
Media Contact: Charleen Wilcox, University of Washington College of Education, Director for Marketing & Communications, wilcoxc@uw.edu