An Emotion-aware Framework for eLearning Systems

The success of an eLearning system is largely influenced by its ability to cater to the learning pattern and condition of a person. A great deal of research has been conducted in an attempt to achieve a better insight into a person s learning needs and the factors that can potentially influence the success of information retrieval and its presentation and delivery in eLearning environments. Most of the contemporary eLearning Systems generally focus exclusively on the cognitive factors and are often unable to adapt to real-world situations in which affective factors play a significant role. There is an increased demand for shifting e-learning solutions from pure web-based content delivery to learner-centric teaching environment. For example for those students who are interested, the course can be delivered at high speed with extra learning material ; while for those who feel disappointed more detailed explanation or simple illustrations could be added; and for those who feel bored funny and stimulating smart activities could be introduced to attract their attention. In this paper we explore the role of affective computing techniques in the development of eLearning Systems. We investigate the possibility of incorporating the Emotion-Handling Module (EH module) into the eLearning environment to make the learning content more relevant and responsive to needs of learners with different abilities and behaviors. For the purpose of our study we take into consideration eight emotional states (interest, engagement, confusion, frustration, disappointment, boredom, hopefulness, satisfaction) which are more relevant in eLearning systems than Ekman s six basic emotions. We investigate the utility of Support Vector Machine-based emotion detection technique for identification of emotions. Finally we propose a framework for eLearning systems (assuming continuous textual feedback from the learner) which is affect-aware through incorporation of Emotional Relevance/Category information to customize and enrich the delivery content as per the mood of the learner.

Keywords:

eLearning , Emotion Detection , Support Vector Machine , Content delivery , Affective Computing