Learning via Facial Expressions
In our electronic era online tutoring and even degrees are becoming more and more reputable and sought after. A few years ago this type of learning was thought to be less beneficial than the traditional classroom/teacher setting.
Is it just as effective to learn online as it is in the classroom?
New software has been developed that aims at bridging the gaps between human interaction and technology.
Researchers at North Carolina State University have created a new program coined “JavaTutor” that tracks how students feel as well as the effectiveness of online courses via facial expressions.
With growing classroom sizes (in both college and grammar school) and a variety of skill levels in each class, many teachers have a difficult time delineating which students are really getting the material and which are lost. This new technology could alleviate that problem for online schools, tutoring companies and regular classrooms by acclimating learning and online courses to the lifestyle of today’s youth.
PsychCentral reported that 65 college students were tracked using this automated Computer Expression Recognition Toolbox (CERT) to evaluate their facial expressions as they were engaged in a one-on-one online tutoring session. The students were tested before and after each tutoring session as well as asked their feedback on how effective they felt the tutorial was as well as how much they learned.
“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.”
Data from CERT as well as student assessments and test scores were used in creating models to predict how effective a tutoring session was based on the student’s facial expressions that indicated feeling’s of frustration or engagement.
MIT Technology Review also commented that ‘this hints at what could prove to be a broader revolution in the application of emotion-sensing technology. Computers and other devices that identify and respond to emotion—a field of research known as “affective computing”—are starting to emerge from academia.’
The Computerized Expression Recognition Toolbox (CERT) was able to identify facial movements associated with learning-centered emotions, such as frustration or concentration and the automated program’s findings were consistent with expert human assessments more than 85% of the time.
Co-author of the study Kristy Boyer, Ph. D. noted, “This work is part of a larger effort to develop artificial intelligence software to teach students computer science.”
If JavaTutor technology proves to be effective for online tutoring sessions this could have huge implications for schools across the nation. Many schools fall short of test score expectations and as a result of that they are labeld Title 1 schools and must offer their students free tutoring sessions that are paid for by the state.
If this software engages and teaches material effectively it could replace expensive tutors throughout the nation and have a huge impact on middle schools, high schools, adult education as well as college courses.