math cornell

Computers may help K-8 math teachers understand students’ thought processes

New research could shed light on the way students approach math problems

Cornell University computing and information sciences researchers are working on computer software that may help K-8 math teachers with grading math assignments.

Researchers will present their research at the Conference on Human Factors in Computing Systems, April 21-26, in Montreal.

“I’ve been interested in working on techniques for automatic education and trying to make teachers’ lives easier,” says Erik Andersen, assistant professor of computer science. “Teachers spend a lot of time grading, but grading is more complicated than is the answer right or wrong. What the teachers are spending a lot of time doing is assigning partial credit and working individually to figure out what students are doing wrong. We envision a future in which educators spend less time trying to reconstruct what their students are thinking and more time working directly with their students.”

Andersen has been working with Sumit Gulwani of Microsoft Research on “doing cool things” with programming by example. “The work is trying to reverse engineer your thought process. We build an algorithm that infers and reconstructs how the student is doing their homework—we are translating intent,” says Andersen.

Laura Ascione

Want to share a great resource? Let us know at