Issue No. 04 - July/August (2007 vol. 22)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/MIS.2007.69
Winslow Burleson , Arizona State University
Rosalind W. Picard , MIT Media Lab
A 2 × 2 experiment investigated the effect of elements of an affective learning companion's emotional intelligence on 76 participants aged 11 to 13 during a challenging problem-solving activity. The experiment contrasted use of an agent showing sensor-driven nonverbal mirroring with one showing prerecorded nonverbal interactions and, separately, affective support versus task support interventions. The experiment examined the effect of emotional intelligence, in terms of the presence of active listening, delivery of appropriate interventions, and type of nonverbal interactions, on the participants' experience, including frustration, perseverance, intrinsic motivation, and meta-affective skill. The hypothesized effects of interacting with a more versus less emotionally intelligent agent didn't hold true at the group level; however, the authors found significant gender differences. The results emphasize the importance of appropriately coordinating the relationships between affect- and task-based intervention and nonverbal mirroring with respect to the affective state of girls and boys. This article is part of a special issue on intelligent educational systems.
affective learning companion, intelligent tutoring system, agent, gender, metacognition, emotional intelligence
W. Burleson and R. W. Picard, "Gender-Specific Approaches to Developing Emotionally Intelligent Learning Companions," in IEEE Intelligent Systems, vol. 22, no. , pp. 62-69, 2007.