Tuesday, January 5, 2010

Emotion-Sensitive Tutoring Software

Researchers at the University of Massachusetts Amherst and Arizona State University in Tempe are developing emotion-sensitive tutoring software which can translate and respond to students emotional cues.

The Project is built around an intelligent-tutoring system known as Wayang Outpost. The system is based on hundreds of sensors embedded in the computer, students’ chairs, and other aspects of the students’ learning environment, e.g.:
  • bracelets worn around the wrist detect changes in students’ pulse and in moisture levels on the surface of the skin;
  • sensors embedded in the chair cushions identify the nine different postures a learner might take;
  • the computer mouse has pressure-sensitive sensors signal whether a student is squeezing harder in possible frustration.
Further project data is collected through a video camera embedded on the computer, with a focus on the student’s "eyebrows, mouth, and nose, discerning whether the learner is smiling, frowning, or yawning".

The researchers find that the umbrella of data collected through the sensors allows the system to correctly identify variation in students’ emotions more than half the time. And when the program responds to students' emotions it does so via a "pedagogical agent" - bhasicall, characters or avatars who will register the emotion being experienced and provide an appropriate array of responses.

Major investors in emotion-sensitive tutoring software research include the National Science Foundation and the U.S. Department of Education’s Institute of Education Sciences. While classroom use of this type of software is still a ways off, researchers see practical application happening within the next five to ten years.

The availability of studies on whether students learn more with emotion-enhanced computer tutors than they do with the other kinds of computer tutors is still somewhat thin, but "some early results from small experiments around the country [United States] show promise".