As a guest user you are not logged in or recognized by your IP address. You have
access to the Front Matter, Abstracts, Author Index, Subject Index and the full
text of Open Access publications.
Software engineering usually involves the collaboration of team members in a team. One important issue of project leaders or software engineering trainers is to form teams that will collaborate efficiently. In view of this, in this paper we describe how we have adapted the stereotype-based theory for building individual user models in a collaborative learning environment in order to provide intelligent help to trainers of UML. In this work, we describe the user characteristics included in the user models and the type of advice offered to the human trainer of the system. The user characteristics are related not only to the knowledge state of the users, but also to their personality and performance types. The advice concerns the most effective organization of the users into groups taking into consideration their level of expertise, their personality characteristics and their performance types. Furthermore, we present an empirical study among experienced trainers on the combinations of stereotypes that are considered to be the most appropriate matching of the users.