Overview

The Learner Data Institute (LDI) is a National Science Foundation (NSF) funded project to lay the foundation of a Data Science institute for learner data.

Read an Overview of LDI (LDI@EDM 2020)

This National Science Foundation (NSF)-funded project, led by Dr. Vasile Rus, William Dunavant Professor in Computer Science at The University of Memphis, and Dr. Stephen Fancsali, Director of Advanced Analytics at Carnegie Learning, Inc., will lay the foundation for a future Learner Data Institute (LDI).

LDI mission will be to harness the data revolution to better understand how people learn, improve adaptive instructional systems (AISs), and make the learning ecosystem more effective and cost-efficient. LDI’s primary focus will be online learning with AISs and blended learning classroom environments in which AISs play a key role alongside classroom teaching and learning, seeking data-driven innovations that make experiences in both contexts more effective and engaging for teachers and learners. LDI will build on previous efforts and cyber-learning infrastructure, including MATHia®, Carnegie Learning’s widely-deployed K-12 artificial intelligence-driven mathematics tutoring software, two NSF-funded projects, the LearnSphere/DataShop project and the SPLICE (Standards, Protocols and Learning Infrastructure for Computing Education) project, as well as the Advanced Distributed Learning (ADL) Initiative, a DoD-wide program and the U.S. Army Research Laboratory’s Generalized Intelligent Framework for Tutoring (GIFT) project.

The two-year conceptualization phase focuses on building a strong community of interdisciplinary researchers, defining research priorities and developing prototype solutions that address student learning, cyber-learning and learning engineering challenges. Contributors from academia, industry and government will work towards building a framework that will facilitate science convergence to accomplish this mission, recognizing that solving critical challenges will involve innovations that synthesize work in a number of different fields. The LDI team will also address a number of specific core educational tasks in the context of online and blended learning environments using advanced methods such as deep learning and statistical relational learning. The proposed data science methods and models are expected to be generally applicable to other instructional contexts as well as other science and engineering areas.

The project’s core team consists of a unique mix of academics, faculty and students, from the University of Memphis and researchers and developers from a research-oriented, commercial provider of computer-based educational services, Carnegie Learning, Inc. The University of Memphis team includes faculty, researchers, students, and developers spanning a wide range of expertise such as Computer Science, Statistics, Cognitive Science, Education, Engineering and Social Work. Carnegie Learning (CL) is a leading developer of adaptive instructional systems, curriculum, and professional services, currently serving more than 400,000 students (primarily in Grades 6-12) and thousands of teachers in more than 2,000 school districts across the United States every year. CL will provide access to vast amounts of data to our LDI team and help implement and deploy in real settings discoveries that the LDI team will generate. The LDI team also includes a group of 13 external partners: 4 additional companies (Aptima, Gooru, SoarTech, Workbay), government research labs (U.S. Army Research Laboratory), and universities (University of Colorado Boulder, University of Wisconsin–Madison, University of Pittsburgh, North Carolina State University, and University of Texas at Dallas).

The project, with a budget of $2,584,309, will involve 40 individuals including six PhD students. For more information on this initiative, contact Rus at vrus@memphis.edu and sfancsali@carnegielearning.com.

Additional Information:

An overview of the Learner Data Institute can be found at the following link: LDI-Overview.pdf.

An brief description of our plan is available at the following link: LDI-Plan.pdf