Detecting students' perception style by using games

Knowing students' learning styles allows us to improve their experience in an educational environment. Particularly, the perception style is one of the most important dimensions of the learning styles since it describes the way students perceive the world as well as the kind of learning content they prefer. Several approaches to detect students' perception style according to Felder's model have been proposed. However, these approaches exhibit several limitations that make their implementation di cult. Thus, we propose a novel approach to detect the perception style of a student by analyzing his/her interaction with games, namely puzzle games. To carry out this detection, we track how students play a puzzle game and extract information about this interaction. Then, we train a Naive Bayes Classi er to infer the students' perception style by using the information extracted. We have evaluated our proposed approach with 47 Computer Engineering students. Experimental results showed that the perception style was successfully predicted through the use of games, with an accuracy of 85%. Finally, we conclude that games are a promising environment where the students' perception style can be detected.