With the massive rise in popularity of online learning platforms like Kno, LearnSmart, and Literati School, one key factor that has been missing from the equation is the ability of a live instructor in a classroom setting to see a student who may have a puzzled facial expression and the swoop down to assist the student. For some students, relying on that interaction can mean the difference between passing and failing, if they complete the course at all.
According to work being done at North Carolina State University, software is being developed that will gauge a student’s interest level and understanding of material presented online. Researchers have developed recognition software that takes cues from users’ facial expressions and provides a somewhat accurate assessment of their knowledge.
“This work is part of a larger effort to develop artificial intelligence software to teach students computer science,” said Dr. Kristy Boyer, an assistant professor of computer science at NC State and co-author of a paper on the work, 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.”
More important than the research and development, though, is the feedback from the actual students who took part in the research. Students were tested on the material presented in a tutorial before and after the learning, and were given self-assessment surveys at the end of the program to judge whether or not the facial images were in line with what learning and attitude outcomes were actually taking place.
According to the release, the report, “‘Automatically Recognizing Facial Expression: Predicting Engagement and Frustration’,” will be presented at the International Conference on Educational Data Mining, being held July 6-9 in Memphis, Tenn. The paper was co-authored by Joseph Wiggins, an undergraduate at NC State; Dr. Eric Wiebe, a professor of science, technology, engineering and math education at NC State; and Dr. James Lester, a professor of computer science at NC State. The research was supported by the National Science Foundation.”