Comparison of Automatic Classification Methods

• Main Authors: Cuo-Yen Lin, 林卓彥
• Other Authors: Sun Wu
• Format: Others
• Language: zh-TW
• Published: 2006
• Online Access: http://ndltd.ncl.edu.tw/handle/56976312770807843280

碩士 === 國立中正大學 === 資訊工程所 === 94 === With the rapid development of internet and the popularity of online internet, we can surf various information what we needed on the internet. But so far the information on the line lack automobile system to categorize them, it needs to categorize them by artificialities. In this thesis, I try to analyze these main methods and test categorization. I want to present they are effective and view its result. In this thesis, we try to decide two comparisons of automatic classification methods. One is KNN, another is SVM. At first, I will collect lots of data about news websites to analyze. I chose Vector Space Model as the main structure. Then, I try to parser different pages to test KNN and SVM these two methods，Finally, precision will compare and contrast the difference , the advantage and disadvantage.