Recommendations-based on semantic analysis of social networks in learning environments

The expansion of social utilization within web applications provides a set of social media that allows users to
contribute freely and interact with each other. Consequently, E-learning systems have benefited greatly from the
concepts of the social web and the emerging technologies of the web semantic, where students and teachers are
living and interacting mainly in the world of Web 2.0 and social networks. Especially, the Web semantic provides
content that is understandable by machines and Web 2.0, which help to develop collaborative services. Further it
can be integrated in a single social structure semantics that could be a good tool to improve the quality of learning.
Our goal is to show that these technologies can be adopted to improve the e-Learning user experience and
to provide a full automatic learning platform called iLearn. We present a learning environment formulated as a
social network, in order to carry out an automatic semantic reasoning including the interactions between users
as well as their relationships with the provided learning resources. We merge the analysis of social networks with
the web semantics to go beyond the analysis of social graphs by integrating a treatment semantics of the knowledge
that they contain and designed by the ontology formalism. iLearndevelops two ontologies, the first helps
to understand the feeling of users versus resources and recommendations, whereas the second categorizes the
different resources. In particular, we present an interactive method of detecting communities to provide students
belonging to the same learning community the best learning strategies, the strong collaborators candidates, and
the relevant resources that meet well within their needs.