Research On Ontology-based Scientific Papers Of Chinese Classification

With the rapid development of technology and society, academia tends to be informationization. The Internet retrieve becomes an important way to obtain relevant information for a vast number of scholars. Therefore, how to find the scientific papers quickly and accurately in the electronic knowledge base has become a research focus for many scholars, and increasingly attentioned by them. Text classification plays an important role in many information retrieval systems and text minings, it can improve the retrieval performance, provide browsing and navigation mechanisms and discover similar text opporturely.Based on studying the background and present situation, discussed the basic knowledge of text categorization, the pretreatment of text categorization, the feature extraction algorithm of text classification and several commonly used text classification algorithm. For the organizational structure of chinese scientific papers. We proposed the particuler feature extraction alglorithm based on hierarchieal feature extraction algorithm to extract feature words. Meanwhile, this thesis introduced ontology which has a good level of logical reasoning and conceptual support and achieved semantic informations through the relationship between the concepts to improve the classification accuracy. We constructed information Science ontology, discussed the guidelines of ontology construction, tools of ontology construction, construction methods and ontology description language.Finally, we give the ontology-based classification framework of Chinese scientific papers, the improved of the pretreatment method, the new feature extraction algorithm and the information science ontology applied to the whole process of the framework for the experiment. Experimental results show that the proposed method has good effect in recall, precision and F1 value.