In modern Economies, knowledge management systems (KMSs) applications are gradually adopted from a growing number of enterprises, organizations and governments. As digital content availability is increasing dramatically through centralized of distributed digital libraries operation, a great research interest is developed upon ''clever'' knowledge retrieval based on each user's individual preferences. Modern man usually requests to get knowledge under time pressure. In many cases it is not possible to have enough time to evaluate extensively the huge amount of results presented after a ''string-based'' criteria query to a digital library. Next generation KMSs should be able to eliminate the results of a search query, based on a certain user's profile. This profile carries information about the level of preexistent knowledge that maybe a user has on a certain knowledge area, the exact scope of its research and the time that he has available in order to exploit the results of this research. In this paper a new generation of KMSs is proposed that are supporting personalized knowledge retrieval. This is achieved through an innovative architecture of enriched knowledge objects for knowledge representation and the development of an expert system for diagnosis and dynamic knowledge composition.

In this review paper, we computationally analyze a vast volume of published articles in the field of Adaptive Learning, as obtained by the Scopus Database. Particularly, we use a query with search terms targeting the area of Adaptive Learning Systems by utilizing a combination of specific keywords. Accordingly, we apply a multidimensional scaling algorithm to construct bibliometric maps for keywords, authors, and references. Subsequently, we present the computational results for the studied dataset, reveal significant patterns appearing in the field of adaptive learning and the inter-item associations, and interpret the findings based on the current state-of-the-art literature in the area. Furthermore, we demonstrate the time-series of the evolution of the research terms, their trends over time, as well as their prevalent statistical associations.

No abstract