Keywords extraction for automatic indexing of e-learning resources

With the growing use of various educational web applications such as e-Learning platforms, learning portals, learning object repositories, ... as well as the increasing setting on line of learning resources, it becomes essential to index these resources in order to facilitate their searching and retrieving. In this paper, we address the problem of automatic indexing of online educational resources and we propose an approach to help the indexing operation. This approach consists in automatically extracting a set of relevant terms describing the educational content of a resource. The proposed approach is based on the TF-IDF algorithm, the usage of a domain lexicon and exploits the structure of educational documents.