Exploring e-Learning Knowledge Through Ontological Memetic Agents

E-Learning systems have proven to be fundamental in several areas of tertiary education and in business companies. There are many significant advantages for people who learn online such as convenience portability, flexibility and costs. However, the remarkable velocity and volatility of modern knowledge due to the exponential growth of the World Wide Web, requires novel learning methods that offer additional features such as information structuring, efficiency, task relevance and personalization. This paper proposes a novel multi-agent e-Learning system empowered with (ontological) knowledge representation and memetic computing to efficiently manage complex and unstructured information that characterize e-Learning. In particular, differing from other similar approaches, our proposal uses 1) ontologies to provide a suitable method for modeling knowledge about learning content and activities, and 2) memetic agents as intelligent explores in order to create "in time" and personalized e-Learning experiences that satisfy learners' specific preferences. The proposed method has been tested by realizing a multi-agent software plug-in for an industrial e-Learning platform with experimentations to validate our memetic proposal in terms of flexibility, efficiency and interoperability.