An ontology for predicting students' emotions during a quiz. Comparison with self-reported emotions

Abstract

Recent research suggests that predicting students' emotions during e-learning is quite relevant but should be situated in the learning context and consider the individual profile of users. More knowledge is required for assessing the possible contributions of multiple sources of information for predicting students' emotions. In this paper we describe an ontology that we have implemented for predicting students' emotions when interacting with a quiz about Java programming. An experimental study with 17 computer science students compares the automatic predictions made by the ontology with the emotions self-reported by students.