„Good morning Student, you’re just in the right mood for learning!“
In a near future students may hear this good morning when they sit down to learn.
Emotions are already recognized by computers. There is some good software for automated emotion recognition in human faces (see examples below). In the last fifteen years appeared an increasing amount of papers about automated facial emotion recognition and tools to detect emotions in faces using photos, webcams, lifestreams, and videos. As an example, look at a demo version of the Face Analysis Cloud Engine (beta version) of sightcorp: https://face.sightcorp.com/demo_analysis_display/.
Successful learning is a difficult task. It takes place, only if a person is ready for learning. Emotions take a very important part in it. In our limbic system, we appraise everything we do and everything that happens do us, if it is good or bad for us (Roth, 2009). So, emotions facilitate and hinder learning.
Generally, learning does not just happen. It is an active process. When Student enters a learning situation he does not beginning at point zero. He brings learning experiences, personal characteristics, and preexisting knowledge. Therefore, he will perceive the qualities of the learning environment and the learning content in his own way and experience his own emotional reactions and appraise the system and learning content. The learning content gets into working memory with its limited capacities. The larger the intrinsic load (e.g. difficulty of the learning content) and the extraneous load (e.g. bad usability), the less Student will learn. Emotions also influence the learning process. That happens directly (e.g. the emotional arousal is high) and indirectly via the appraisal of content and system (e.g. positive emotions can increase interest). Brief, lower cognitive load and positive influence of emotions lead to a better learning performance. This short description of our theoretical framework is based on several models and theories about memory and learning.
If the learning system ‚knows‘ that Student is in the mood for learning or not, it can adapt the learning content or/and the learning environment or it can recommend the best learning activities corresponding to Students emotions. To do this a lot of research has to be done. One of the central points is measuring emotions in a practical way. Mauss and Robinson (2009) recommend measuring emotions on different levels. In our research we will use among other measures questions about immediate subjective experiences and automated recognition of facial emotions.
„Reader, you seem tired. Let’s take a short brake.”
Examples of facial emotion coding software: