A Taxonomic Relationship Learning Approach for Log Ontology Content Event

摘要

To construct the log ontology is one of the main tasks of semantic Web usage mining. In order to discover the hierarchy of users' visit interesting for web sites, we propose a taxonomic relationship learning approach for content events on log ontology. In this method, event is used to express the users' visiting action, and content event is the semantic behavior of users' visiting to the page content of sites. This method extracts the taxonomic relationship of content event by web document cluster based on swarm intelligence, which combines web content mining and web usage mining. This method improves the results of semantic Web usage mining and provides more decision-making for optimizing the structure of Web sites. The simulation experimental results show that this method is effective and quite feasible to solve practical problems.