Researchers at the University of California, Irvine have developed a new way to measure student attention during remote learning. The method uses a combination of computer vision and machine learning to track students' eye movements and facial expressions.

The researchers say their method is more accurate than traditional methods of measuring attention, such as surveys or self-reporting. It can also be used to track attention in real-time, which allows teachers to make adjustments to their teaching if students are not paying attention.

The study, which was published in the journal "Educational Technology & Society," involved 100 students who were taking an online course. The students were asked to complete a series of tasks while their eye movements and facial expressions were recorded.

The researchers found that students who paid more attention to the course material were more likely to get good grades. They also found that students who were distracted by other things, such as their phones or social media, were less likely to get good grades.

The researchers say their method can be used to help teachers identify students who are struggling to pay attention. It can also be used to develop new ways to improve student attention during remote learning.

"Our method provides a more objective and reliable way to measure student attention than traditional methods," said study lead author Dr. Mingyu Wang. "This information can be used to help teachers improve their teaching and to identify students who need extra support."

The researchers say they plan to continue to develop their method and to explore its use in other educational settings.