Towards an Emotion Labeling Model to Detect Emotions in Educational Discourse

In a collaborative e-learning environment, students are usually involved in learning activities such as collaborative writing (e.g., an essay in Wiki form) and debates in the form of a chat or asynchronous forum. Capturing students´ feelings and emotional states enclosed in such textual information is important, since sentiments can influence individual behavior and consequently group dynamics as well as individual and group performance. For this reason, emotion awareness becomes an important issue for both tutors and students themselves. Especially for tutors, if they have as accurate affective information as possible about the emotional state that every individual and group is encountered, they might be able to provide more effective feedback to the students that includes not only cognitive but also affective scaffold. A first important step to this endeavor is to develop an approach that enables labeling affective behavior and then presenting the emotional information to all the actors involved in the learning process.