A High Level Architecture for Personalized Learning in Collaborative Networks

In Collaborative Network (CN) environments, creation of collective understanding about both the aimed outcome and the procedure for achieving it by its members is the antecedent to any successful co-working and codevelopment. While a part of the common CN knowledge is pre-existing to its establishment, once the collaboration activities begin the emergent knowledge also needs to be commonly understood within this environment. Creating such commonality in understanding is however quite challenging. This paper suggests a bottom-up approach to reach collective understanding by all individuals involved in these networks, namely by the staff involved at all organizations which participate in the CN. The proposed approach is founded on the idea of learning-together by the CN members to reach their collective understanding. In this approach, the domain/application experts in the CN act as the instructors and content providers, and assist with the modeling/remolding of the education domain for the CN environment. Considering that the individuals involved in the CN are highly diverse and have different backgrounds, their learning requirements are also highly varied. Aiming to reach common understanding in CNs, this paper first addresses the main challenges in this area of learning; it then presents the related state-of-the-art and proposes a high level architecture for personalized learning of the members in collaborative networks.