E-learning students tend to get jaded and easily dropout from online courses. Enhancing the learners' experience and reducing dropout rates in these e-learning based scenarios is the main purpose of this study. This paper presents the results obtained so far and preliminary conclusions. In a first stage, the objective was to study the background and state of the art of these educational scenarios. In a second phase, identifying key reasons for dropouts, through a survey and interviews, was the aim to understand and detect motives and behavior patterns of students with dropout thoughts. Finally, developing, testing and validating a functional prototype of an Intelligent Tutoring System will allow to evaluate concepts, collect statistical information on its effectiveness, analyze and discover if course completion rates are improved.