Cooperation Systems
Fraunhofer Institute for Applied Information Technology FIT
CAPLE – Context and Attention in Personalized Learning Environments
The CAPLE group focuses on task independent support of individualized learning experiences. The approaches are based on observations about and context of the learner in learning situations. Information is plenty today, with a continuously growing number of information sources and new ways to interact with them. Learners need to focus more and more on managing digital information. Consequently, the cognitive load of learners increases severely beyond meaningful states. Cognition and learning is dependent on the information provision and the learning processes.
The critical element is attention that enables to utilize this type of processes. CAPLE provides the necessary foundations and models for contextualized attention metadata (CAM) to enable individualized and personalized learning experiences tailoring information provision as well as collaboration to the individual needs and tasks at hand. CAM is captured from observations of user-driven activities like the handling of digital information in learning and workplace scenarios.
CAPLE extends the research activities of Fraunhofer FIT by focusing specifically on research on attention-aware contextualized learning not addressed so far. It focuses on the human being in Life Long Learning (LLL) scenarios embedded in our fast paced society that relies on IT to communicate, exchange and produce knowledge. The aim of the CAPLE research group is to reduce and manage the information overload according to the persons’ needs and demands.
Challenges
By observing the user, we model her focus of attention. Interpreting attention as transferred statements about what a user is working on in which contexts, we support the user in concentrating on the right information at the right time.
To model the user’s behavior, her usage on the level of application handling is observed. CAM represent how a learner deals with specific information in specific contexts. By integrating the observations about the activities of the user in her digital environment, the context is described. Analysis of data requires longitudinal research to gain personal information, e.g. in order to find repeating patterns in the user’s behavior in her work with digital information.
To draw conclusions, the collected data is integrated and analyzed using existing and newly developed, more appropriate algorithms. Correlating content and context of observations along changing environmental and psychological states requires the development of flexible and scalable user models.
The feedback of the conclusions about the user to the user is a core element in CAPLE. The user is in control of the help the system provides and able to accept or deny the proposed improvements. In this way, meta-cognition is supported, which means that knowledge about the user’s own strategies will be extended. The self-awareness leads to a better self-regulation and higher feeling of control.
Contextualized Attention Metadata (CAM)
The CAM format was developed to capture the users' foci of attention on different applications. The CAM schema is an open specification to capture data on how people use information in browsers, web pages, news feeds and blogs. It describes which data objects attract the users’ attention, which actions users perform with these objects and what the use contexts are.
Social Bookmarks