The paper entitled Development of an Affect-Sensitive Agent for Aplusix by
Thor Collin Andallaza and Ma. Mercedes Rodrigo was accepted as a short paper
and poster at the Artificial Intelligence in Education Conference 2013 to be
held at the University of Memphis from July 9 to 13.
The abstract of the paper is as follows:
We compared two versions of an affect-sensitive embodied conversational
agent for Aplusix, an intelligent tutoring system for algebra. Version 1 of
the agent was able to detect and respond to user affect, but it responded
too quickly and too frequently. The second version of the agent featured new
student models for detecting and responding to student affective states,
which is less sensitive compared to the first version. We conducted a field
test with students to determine its effect on learning and learning
experience in comparison to using Aplusix alone and Aplusix with the version
1 agent. Results show that version 2 provided significantly fewer
interventions to engaged students, more evaluations of engagement, fewer
evaluations of boredom, and was generally preferred over version 1.
