UBC Computer Science Professor Cristina Conati, postdoc Sebastien Lalle, and their colleagues from North Carolina State University, won the 2016 Best Paper Award at the International Conference on Intelligent Virtual Agents. The paper, titled 'Impact of Individual Differences on Affective Reactions to Pedagogical Agents Scaffolding', explores how understanding students' emotions could be used to design more emphatic and personalized pedagogical agents that could adapt to students' learning goals and personality traits.
Students’ emotions are known to influence learning and motivation while working with agent-based learning environments (ABLEs). There is limited understanding, however, of how intelligent Pedagogical Agents (PAs) impact students’ emotions, what those emotions are, and whether this is modulated by students’ individual differences (e.g., personality, goal orientation). Such understanding could be used to devise more emphatic intelligent PAs that can recognize and adapt to the relevant students' differences in order to enhance their experience with learning environments. In this paper, we investigate the relationship between individual differences and students’ affective reactions to four intelligent PAs available in MetaTutor, an ABLE designed to scaffold effective metacognition and self-regulated learning
We show that the learning trait know as achievement goals (i.e., having a mastery vs. performance goal when learning) as well as a set of personality traits can significantly modulate students’ affective reactions to the Meta-Tutor's PAs. These findings suggest that students may benefit from personalized PAs that adapt to their learning goals and personality traits, and help identify guidelines on which form this adaptation should take.