Personal information agents have emerged in the last decade to help users to cope with the increasing amount of information available on the Internet. These agents are intelligent assistants that perform several information-related tasks such as finding, filtering and monitoring relevant information on behalf of users or communities of users. In order to provide personalized assistance, personal agents rely on representations of user information interests and preferences contained in user profiles. In this paper, we present a summary of the state-of-the-art in user profiling in the context of intelligent information agents. Existing approaches and lines of research in the main dimensions of user profiling, such as acquisition, learning, adaptation and evaluation, are discussed.

Learning styles encapsulate the preferences of the students, regarding how they learn. By including information about the student learning style, computer-based educational systems are able to adapt a course according to the individual characteristics of the students. In accomplishing this goal, educational systems have been mostly based on the use of questionnaires for establishing a student learning style. However, this method has shown to be not only time-consuming but also unreliable. A genetic algorithm approach to automatically identify the individual learning styles of students based on their actions while attending an academic course is presented in this paper. The application of a genetic algorithm to this domain allows us to both discover the learning styles of individual students as they attend different academic units, as well as track the changes on these styles that might occur over time.