A Time for Emoting: When Affect-Sensitivity Is and Isn’t Effective at Promoting Deep Learning
Sidney D’Mello, Blair Lehman, Jeremiah Sullins, Rosaire Daigle, Rebekah Combs, Kimberly Vogt et al.
We have developed and evaluated an affect-sensitive version of AutoTutor, a dialogue based ITS that simulates human tutors. While the original AutoTutor is sensitive to learners’ cognitive states, the affect-sensitive tutor is responsive to their affective states as well. This affective tutor automatically detects learners’ boredom, confusion, and frustration by monitoring conversational cues, gross body language, and facial features. The sensed affective states guide the tutor’s responses in a manner that helps students regulate their negative emotions. The tutor also synthesizes affect via the verbal content of its responses and the facial expressions and speech of an embodied pedagogical agent. An experiment comparing the affect-sensitive and non-affective tutors indicated that the affective tutor improved learning for low-domain knowledge students, particularly at deeper levels of comprehension. We conclude by discussing the conditions upon which affect-sensitivity is effective, and the conditions when it is not.
The final publication is available at Springer via https://doi.org/10.1007/978-3-642-13388-6_29.