Teaching software spots bored or bewildered pupils

New teaching software responds to pupils’ emotional states and is so effective it out-performs novice human teachers.

Developed by University of Notre Dame Assistant Professor of Psychology Sidney D’Mello and colleagues from the University of Memphis and MMIT, AutoTutor and Affective AutoTutor can gauge the student’s level of knowledge.

They ask the student probing questions, analyze the responses, proactively identify and correct misconceptions and respond to the student’s own questions, gripes and comments.

They can even sense a student’s frustration or boredom through facial expression and body posture, and dynamically change strategy in  response.

“Most of the 20th-century systems required humans to communicate with computers through windows, icons, menus, and pointing devices,” says D’Mello.

“But humans have always communicated with each other through speech and a host of non-verbal cues such as facial expressions, eye contact, posture, and gesture. In addition to enhancing the content of the message, the new technology provides information regarding the cognitive states, motivation levels, and social dynamics of the students.”

AutoTutor teaches complex technical content in Newtonian physics, computer literacy and critical thinking by holding a conversation in natural language, and its creators say it can simulate the teaching and motivational strategies of human tutors.

Affective AutoTutor adds emotion-sensitive capabilities by monitoring facial features, body language, and conversational cues and responding to negative states such as frustration and boredom.

It even displays emotions itself, through the content of its verbal responses, its speech intonation and its facial expressions.

In tests on over one thousand students, says the team, AutoTutor delivers learning gains of approximately one letter grade – outperforming novice human tutors, and close to the performance of expert human tutors.

“Much like a gifted human tutor, AutoTutor and Affective AutoTutor attempt to keep the student balanced between the extremes of boredom and bewilderment by subtly modulating the pace, direction, and complexity of the learning task,” says D’Mello.