November 19, 2015

Carnegie Mellon’s “LearnSphere” Aims to Become a Trusted Student Data Repository

in Bloom, the Gates Foundation-funded nonprofit organization, hoped to be a repository of student data educational software makers and researchers could use to improve educational technology, but concerns about the privacy of student data led to its shutdown in 2014. Now, Carnegie Mellon University is leading a new project that addresses the same goal without the privacy risks, according to The Hechinger Report.

Like in Bloom, this $5 million, federally funded project known as LearnSphere seeks to become “the biggest open repository of education data in the world,” but aims to do so without using any student names, addresses, zip codes, social security numbers, or race, family income, or special education designations.  Instead of collecting such data, LearnSphere proposes to collect “the data of keyboard clicks.”

Specifically, it will track students’ keystrokes as they use educational software to “answer questions, hit backspace or sit idly daydreaming and uninterested” and store the data in a virtual warehouse researchers can access from any computer. Keystroke data tells researchers how many times a student repeats or practices an exercise before it becomes knowledge.

LeanSphere’s planners aren’t “building a physical warehouse in a single location” to store all the data. Instead, “those who want to share data can upload it to one of the sites that LearnSphere is managing, or they can keep it on their own server and control who gets access to it.”  Ultimately, the goal is to “build a ‘distributed infrastructure,’ which allows researchers to access data on someone else’s computer,” Hechinger stated.

Carnegie Mellon predicts that it will take at least a year for LearnSphere to be ready for launch.
Read the The Hechinger Report article: