Proceedings of the 2013 international conference on Intelligent user interfaces
Knowledge Elicitation Methods for Affect Modelling in Education
International Journal of Artificial Intelligence in Education
Hi-index | 0.00 |
We conducted a study where 42 participants wrote two essays on opposing stances about abortion (pro-choice and pro-life). Participants' affective states were tracked at 15-second intervals via a retrospective affect judgment protocol. The results indicated participants experienced more boredom when writing essays that did not align with their positions on abortion, but were more engaged when there was alignment. Participants also reported more curiosity while writing pro-choice essays. Importantly, boredom, engagement, and curiosity were the affective states that predicted essay quality.