Extracting Emotions from Texts in E-Learning Environments

摘要: Affective and emotional factors seem to affect student motivation and, in general, the outcome of learning process. By detecting managing emotions underlying a activity it would be possible contribute improve performance. In this work we explore different possibilities aimed at automatically extracting from texts. We present case study which twelve essays written by fresher along her first semester college are analyzed. Those results support idea using non-intrusive emotion detection for providing feedback students. An example use an existing context-based adaptive e-learning system is presented. Incorporating type systems broadens their possibilities, allowing dynamic recommendation activities according each time, as well emotion-based content adaptation, among others.