McGraw-Hill Education has launched a research program designed to explore the use of advanced analytics and data-mining techniques that will help enhance college-student success rates in gateway science, technology, engineering and mathematics (STEM) courses.
The initiative, unveiled Monday at SXSWedu, will be coordinated jointly by the company’s recently formed Learning Science Research Council and Colorado State University.
“McGraw-Hill Education is seeking a wide range of collaborations with institutions like Colorado State to deepen our collective understanding of how to effectively use technology to improve learning outcomes,” said David Levin, president and CEO of the organization. “We want to make our researchers and extensive resources available to test new theories and content in real-world educational settings – to solve real-world education problems.”
Unsuccessful completion of STEM courses – when a student drops, fails or withdraws from a class – is often associated with significantly lower retention and graduation rates, program officials said. Capitalizing on its research expertise, Colorado State chose to work with McGraw-Hill Education to find new ways to use learning analytics to strengthen learning outcomes for its students taking these courses.
Patrick Burns, chief information officer at Colorado State, said that learning analytics is rapidly emerging as an important area of academic research.
“By working with McGraw-Hill Education’s researchers, we hope to discover new techniques for solving the persistent challenge of high attrition rates in STEM gateway courses,” Burns said. “We expect that the research will also benefit other courses and allow faculty to access data and insights in novel ways for enhancing teaching effectiveness.”
The research study, which is currently underway at Colorado State, is concentrating initially on testing and validating predictive models that can help instructors identify at-risk students with whom they can work more closely to ensure course completion.
“We are already starting to see some exciting results and look forward to incorporating our findings in new practical applications,” said Dave Johnson, director of research and analytics for Colorado State University Online. Preliminary results from the project are expected in the first half of this year.
“Through our collaboration with McGraw-Hill Education, we are looking at how we can provide instructors with actionable, data-driven insights that will allow them to help students, at all levels, successfully complete their courses,” he said.
The learning analytics initiative is the first academic research project under the Learning Science Research Council, a new group that was organized by McGraw-Hill Education to promote further research to help inform the continued growth and refinement of technology-supported learning. The council is comprised of senior researchers from McGraw-Hill Education, the Massachusetts Institute of Technology, the University of Massachusetts at Amherst, the University of Memphis, the University of Pennsylvania and University College London’s Knowledge Lab.
The council is focused on four key areas of research:
- Learning analytics:applying data science to generate predictive models and actionable insights for learners and instructors
- Learning algorithms:creating personalized algorithms based on learning science to help students learn better
- Learning quality:applying statistics rigor to evaluate and improve the quality of learning content and assessment
- Learning efficacy:incorporating causal inferencing and modeling methodologies for establishing learning efficacy