Using technology to personalize learning has been identified as a “grand challenge” by the U.S. Department of Education, the National Science Foundation and the National Academy of Engineering. We have known for a long time that one-on-one instruction produces the best outcomes. If every student could work individually with his or her teacher, achievement levels would soar!
The goal of the VLL is to evaluate the potential of a new data-driven approach to building personalized learning systems. Using informatics and machine learning methods, students are automatically guided through the material based on their similarity to prior students who were successful. The more students that use a system, the better its performance should get!
The methods developed by the VLL will go beyond the current state of the art in technology-based learning. “Intelligent tutoring systems” (ITS) are designed to mimic what an expert human teacher would do. Although ITS can be effective, they are expensive to build, make students follow predefined instructional pathways, and do not take advantage of the large data sets that accumulate as students work online.