A method for automatic construction of learning contents in semantic web by a text mining approach

Abstract

E-learning has gradually been accepted as an alternative for traditional lecture-based learning. One key factor for the success of e-learning is the possibility of understanding the semantics of learning contents autonomously by machines. The semantic web could naturally fit in according to its ability on information interchange and sharing between machines. Such ability is made possible when the semantic web pages are properly annotated. To transform the existing semantics-lacking learning contents to semantics-enriched ones, we propose a machine learning approach to automatically generate semantic markups for traditional learning contents, which are usually presented in web pages. The proposed method applies the self-organising map algorithm to cluster training web pages and conducts a text mining process to discover the anchor texts to be tagged and their semantic descriptions. Preliminary experiments show that our method may successfully generate semantic markups for the web pages that could be used for e-learning in the semantic web environment.