Carnegie Mellon University has announced that it will participate in a 5-year, $5 million project that will create a large infrastructure in an effort to improve educational outcomes and advance learning.
Sponsored by the National Science Foundation, the project, LearnSphere, will store data showing how students learn in a secure way.
LearnSphere will be able to access over 550 datasets from a variety of databases, including online tutoring systems, MOOCs, and educational games, allowing instructors to improve their teachings and the learning of their students by redesigning their courses to coordinate with learning styles.
“We’ve seen the power that data has to improve performance in many fields, from medicine to movie recommendations,” Ken Koedinger, professor of human-computer interaction and psychology and project leader, said. “Educational data holds the same potential to guide the development of courses that enhance learning. Gathering more of this data also promises to give us a deeper understanding of the learning process.”
LearnSphere received a data driven research award given out by the National Science Foundation as part of the Data Infrastructure Building Blocks (DIBBS) program. In all, 14 awards were handed out totaling $31 million.
“NSF has an ambitious vision for advancing scientific frontiers through an enabling and collaborative data infrastructure,” said Irene Qualters, NSF division director for advanced cyberinfrastructure. “We are particularly pleased that this year’s DIBBs awards include this CMU-led project to build on the NSF-sponsored Pittsburgh Science of Learning Center’s DataShop repository for educational researchers.”
Created in 2004, the Pittsburgh Science of Learning Center studies how people learn. DataShop is the world’s largest open educational data repository.
While DataShop collects most of its data from larger sources such as online tutoring systems and educational games, LearnSphere will add data from other sources like MOOCs.
Koedinger said he would like to make LearnSphere into a distributed storage system, allowing researchers to store their own data on their own servers, offering greater control and confidentiality to groups of researchers. Doing so, Koedinger hopes will influence researchers to share their data.
“We’re trying to create a culture in which scientists will not only be cited for their research findings, but also for their datasets,” Koedinger said.
Researchers also hope to discover how to notice signs of students who are about to drop out so that schools may intervene.
“Learning models based on the wide variety of datasets housed in LearnSphere will enable new forms of personalized, just-in-time support for learning,” said co-investigator Carolyn Rosé, associate professor in the Language Technologies Institute and Human-Computer Interaction Institute at CMU.
In June, Carnegie Mellon was the recipient of a Google Focused Research Award, a multi-year award focused on improving MOOCs, allowing the courses to become as successful as traditional classes by focusing on the learning styles of individual students through data-driven learning.
Through the award, Koedinger was able to use machine-learning techniques that allowed him to personalize MOOCs through a computer program that would see what material that has been mastered, and where more practice is needed.
The Google award will fund research at CMU at $300,000 a year for two year with an option for a third year.