A semantic annotation model for indexing and retrieving learning objects

The internet is an important part of our world. Offering a large and increasing amount of information, people can use it for learning, teaching, etc. Automatic tools for learning information retrieval based on semantic tags have not been effective yet. We propose here a model which aims at automatically annotating texts with semantic metadata. These metadata would allow us to index and extract learning objects from texts. This model is composed of two parts. While the first part consists of a semantic annotation of learning objects according to their categories (definition, example, exercise, etc.), the second one uses automatic semantic annotation. Generated by the first part, the latter aims at creating a semantic inverted index able to find relevant learning objects for queries. To sort the results according to their relevance, we apply the Rocchio's classification technique to the learning objects. We have implemented a system called SRIDoP, on the basis of the proposed model and we have verified its effectiveness.