Using Affect Awareness to Modulate Task Experience: A Study Amongst Pre-elementary School Kids

Computing systems may record facts about users such as their click behaviors, their accuracies, and their rates of recurrence, and may then act on predictions of their behaviors and preferences. However, sequences of key presses and mouse movements do not capture their immediate desires and needs during a task. Affectmediated systems, computing systems that adapt to the emotional state of users, can better respond to these momentary shifts in demand. This paper presents a study of how affect mediation can help improve a user’s task performance. Designed as a children’s game, our experimental system uses facial expressions to regress the user to an earlier, easier game phase according to perceived unease. Through experimentation with child participants, we found that children performed better with the affect-sensitive version of the game than with the non-affect-sensitive version. We hope these results will support the future design of affect-sensitive machines that can help users complete tasks.