Generating Associated Relation between Documents

Traditional text mining techniques have weak ability to provide associated relations with rich semantics that is a foundation of the intelligent browsing of topics, discovery of semantic community and precise personalized recommendation in current Web and knowledge Grid, etc. In this paper we propose an algorithm to generate and calculate the associated relations and their strengths between documents within a domain. Each document is represented by a bag of words and their weights. We first build domain knowledge background based on the association rules at keyword level, and then we apply those association rules to generate and calculate the documents´ semantic relations and their strengths at document level, which effectively shorten the semantic gap from keyword semantics to document semantics. Experimental results show that our proposed method is feasible and able to discover interesting facts within a domain.