The context toolkit: aiding the development of context-enabled applications
Proceedings of the SIGCHI conference on Human Factors in Computing Systems
How Can We Form Effective Collaborative Learning Groups?
ITS '00 Proceedings of the 5th International Conference on Intelligent Tutoring Systems
Recognition of Human Activity through Hierarchical Stochastic Learning
PERCOM '03 Proceedings of the First IEEE International Conference on Pervasive Computing and Communications
Learning to Detect User Activity and Availability from a Variety of Sensor Data
PERCOM '04 Proceedings of the Second IEEE International Conference on Pervasive Computing and Communications (PerCom'04)
Coordinate: probabilistic forecasting of presence and availability
UAI'02 Proceedings of the Eighteenth conference on Uncertainty in artificial intelligence
The fourth man: supporting self-organizing group formation in learning communities
CSCL'07 Proceedings of the 8th iternational conference on Computer supported collaborative learning
Content-free collaborative learning modeling using data mining
User Modeling and User-Adapted Interaction
DynMap+: a concept mapping approach to visualize group student models
EC-TEL'06 Proceedings of the First European conference on Technology Enhanced Learning: innovative Approaches for Learning and Knowledge Sharing
Evaluating automatic group formation mechanisms to promote collaborative learning - a case study
International Journal of Learning Technology
A method to form learners groups in computer-supported collaborative learning systems
Proceedings of the First International Conference on Technological Ecosystem for Enhancing Multiculturality
Hi-index | 0.00 |
An important but often neglected aspect in Computer Supported Collaborative Learning is the intelligent formation of learning groups. Until recently, support for group formation was mostly based on learner profile information. However, the perspective of ubiquitous computing and ambient intelligence allows for taking a broader view on group formation, extending the range of features to include learner context information such as sensor-derived activity and availability. A probabilistic approach has been developed that automatically learns individual characteristics and indicates relevant situations, and which has been tested in a set of experiments.