| 利用本体集成和特征聚类的网页分类研究 |
| |
| 引用本文： | 孙少波.利用本体集成和特征聚类的网页分类研究[J].现代电子技术,2012,35(14):93-96. |
| |
| 作者姓名： | 孙少波 |
| |
| 作者单位： | 西安文理学院计算机系,陕西西安710065;长安大学资源学院,陕西西安710054 |
| |
| 基金项目： | 国家自然科学基金资助项目(60975036) |
| |
| 摘 要： | 网页分类存在着新词多、特征维数高的问题，提出了一种新的网页分类方法。首先利用桥本体对分类领域本体进行集成，建立多本体语义标注模型，对文本特征进行降维。在此基础上，对不同类标号的关健词进行聚类，解决新词无法识别的问题，同时考虑网页标签的不同权重，用改进的SVM模型对中文网页进行分类。实验结果表明，上述方’法改进了传统SVM分类器的性能。
|
| 关 键 词： | 文本分类 本体集成 支持向量机 维数约简 聚类 |
Research of Web-page categorization based on ontology integration and feature clustering |
| |
| SUN Shao-bo.Research of Web-page categorization based on ontology integration and feature clustering[J].Modern Electronic Technique,2012,35(14):93-96. |
| |
| Authors: | SUN Shao-bo |
| |
| Institution: | SUN Shao-bo1,2(1.Dept.of Computer Science,Xi′an University of Arts and Science,Xi’an 710065,China; 2.School of Earth Science and Resources,Chang’an University,Xi’an 710054,China) |
| |
| Abstract: | In Web-page categorization,since the traditional algorithms can not solve the problems of new words and high dimension features identification effectively,a novel method is proposed in this paper.A multi-ontology semantic annotation model based on ontology integration with bridge ontology is put forward for reducing high dimension features,and then |
| |
| Keywords: | from different classes are clustered to solve the problem of new words identification Taking into account of different weighs of HTML tags the improved SVM model is adopted to carry out the Web-page categorization The preliminary experimental results show that the method proposed above has improved the performance of traditional SVM categorizers Key words: text classification ontology integration support vector machine dimensionality reduction clustering |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
