KnowledgeSeeker — an ontological agent-based system for retrieving and analyzing Chinese web articles

In this paper, we present the KnowledgeSeeker, an ontological agent-based system that is designed to help users find, retrieve, and analyze news article from the Internet and then present the content in a semantic web. We present the benefits of using ontologies to analyze the semantics of Chinese text, and also the advantages of using a semantic web to organize information semantically. KnowledgeSeeker also demonstrates the advantages of using ontologies to identify topics. We use a Chinese document corpus to evaluate KnowledgeSeeker and the testing result was compared to other approaches. KnowledgeSeeker is able to identify the topics of Chinese web articles with an accuracy of nearly 87% and has a processing speed of less than one second per article. It is also able to organize content flexibly and understands knowledge more accurately than methods that use ontology definition.