Research on the design and implementation of web mining system
Zhijing Liu · Jisuanji gongcheng yu sheji · 2002
Information overloading is a big problem in the global informatization. The web is huge, but it is difficult to find what we needed on it. We interactive with the web by click or search engines, however neither can helps us get what we want ac-curately and immediately. The web mining techniques can resolve these problems. The theories of web mining are discussed in this paper. Based on the objects, we classify web mining into three categories, namely web content mining, web structure mining, and web usage mining. Finally, we proposed a general frame of web mining systems based on the specific structures of HTML pages. The implementation is also discussed in details.