| Resumo: | Due to the rapid evolution of society, citizens are constantly being pressured to obtain new skills through training. The need for qualified people has grown exponentially, which means that the resources for education/training are significantly more limited, so it's necessary to create systems that can solved this problem. The implementation of Intelligent Tutoring Systems (ITS) can be one solution. Besides, ITS aims to enable users to acquire knowledge and develop skills in a specific field. To achieve this goal, the ITS should learn how to react to the actions and needs of the users, and this should be achieved in a non-intrusive and transparent way. In order to provide personalized and adapted system, it is necessary to know the preferences and habits of users. Thus, the ability to learn patterns of behaviour becomes an essential aspect for the successful implementation of an ITS. In this article, we present the student model of an ITS, in order to monitor the user's biometric behaviour and their learning style during e-learning activities. In addition, a machine learning categorization model is presented that oversees student activity during the session. Additionally, this article highlights the main biometric behavioural variations for each activity, making these attributes enable the development of machine learning classifiers to predict users' learning preferences. These results can be instrumental in improving ITS systems in e-learning environments and predict user behaviour based on their interaction with computers or other devices.
|
|---|