17 September 2011 in User Modeling and User-Adapted Interaction
1 March 2011 in Research and Practice in Technology Enhanced Learning
We compare the affect associated with students learning from an intelligent tutoring system, Aplusix, and a game, Math Blaster 9-12, covering very similar mathematical content. Quantitative field observations of student affect were conducted in classrooms in private schools in the Philippines. Students experienced large amounts of positive affect in both environments. It has been hypothesized that educational games will lead to better affect than other forms of educational software, but it was found that students experienced more positive affect (specifically, engaged concentration) and less negative affect (specifically, boredom) in the intelligent tutor than in the game, though there was a trend towards more delight within the game. These results suggest that intelligent tutors may be more affectively successful than had previously been realized. An alternate possible implication is that games’ motivational benefits are not solely in terms of moment-to- moment affective experience. At the same time, the differential affective benefits of the two genres of educational software suggest that some blend of the two types of learning environments may be more engaging than any existing educational software.
29 November 2010 in International Conference on Computers in Education
We study the relationships between affective states and sequences and learner achievement using sequential pattern mining techniques. We found, in accordance with prior research, that boredom is an undesirable state that is both persistent and detrimental to learning. We also found that confusion punctuated with periods of engaged concentration contributes to learning. However, confusion alone has a negative impact on student achievement, possibly indicating that students are stuck. These results shed light on past results finding inconsistent relationships between confusion and learning.