Facial Expressions To Help Improve Teaching Software

Researchers from North Carolina State University have developed a facial expressions tracking software, which can predict the effectiveness of online tutoring sessions.

Most often than not, teachers often wonder whether their students have actually grasped and understood what they are being taught. Now, researchers from North Carolina State University have developed a software that can solve this problem, at least in online tutoring.

The new facial expressions tracking software assesses the emotions of students engaged in an online tutoring session and predicts how effectively he/she is grasping all the information provided to him/her.

"This work is part of a larger effort to develop artificial intelligence software to teach students computer science," says Dr. Kristy Boyer, an assistant professor of computer science at NC State and co-author of the study in a press release. "The program, JavaTutor, will not only respond to what a student knows, but to each student's feelings of frustration or engagement. This is important because research shows that student emotion plays an important role in the learning process."

The software is an automated Computer Expression Recognition Toolbox (CERT) program, which is used to evaluate facial expressions. For the study, the software was used on 65 college students engaged in one-on-one online tutoring sessions. The CERT was able to pick up emotions associated with learning like concentration and frustration. The detections were accurate 85 percent of the time.

Researchers also took feedback from the participants about how effective they felt the tutorial was. They measured how much the students had learnt by giving them tests both before and after the tutorial sessions.

Authors of the study then combined both these measurements as well the previous observational data from CERT and developed this new software that can predict how effective a tutorial session was, based on what the facial expressions of the students indicated about each student's feelings of frustration or engagement.

"This work feeds directly into the next stage of JavaTutor system development, which will enable the program to provide cognitive and emotion-based feedback to students," says Joseph Grafsgaard, a Ph.D. student at NC State and lead author of the paper.

Real Time Analytics