Event Feature and Personality -Event- Ontology Based for Classifying Chinese Web Pages

摘要

In recent years, more and more experts find that events have more semantic means than any other features, such as, characters, terms and concepts. This paper described a method which used event features to classify Chinese web pages talking about personality in SVM classifier. Firstly, we explained how to represent Chinese documents by event features. Secondly, we constructed event ontology about personality information. We called this event ontology as Personality Event Ontology (PEOnt). Finally, an experiment was presented. This experiment showed that our approach results had an improved classification in terms of precision and recall. This improvement, however, come at a cost in a low features vector space's dimensionality due to the event features and event ontology used.