Research on similarity of Semantic Web
Hongsheng Wang, Xiaoguang Han · 2010
With the rapid increasing of information on Internet and the emergence of the Semantic Web technology, information retrieval based on the Semantic Web has become a researching focus. In the semantic retrieval, the calculating method of semantic similarity is very important to information recall and precision ratio, this paper presents a new calculating method of semantic similarity by improving the flaw of traditional calculating method. The method adopts a directed graph to establish the Semantic Web and calculating the similarity of semantic nodes and semantic relations, then combine them to form the unified semantic similarity values. The analysis of the semantic retrieval and the statistics of the results indicate that this method can get higher recall and precision ratio than traditional method.