Technological advances offer new paradigms for training, allowing novel forms of teaching and learning to be devised. However, several e-learning systems are based on complex procedures and unusable interfaces, which are regarded as intimidating, confusing or simply frustrating by the user. Of course, in such cases their effectiveness is very limited. The quality of interaction, and the design of effective and usable content, are a prerequisite for any type of course accessible through information technology.
Our research in the field of e-learning has focused on the improvement of interaction, obtained mainly by means of perceptual interfaces. Implicit communication can be particularly effective for this purpose, as it is useful to potentially detect emotional states. The recognition of facial features or the observation of ocular parameters can partially compensate for the lack of the teacher in the flesh, identifying potential student problems and acting accordingly.