| Summary: | 碩士 === 世新大學 === 資訊管理學研究所(含碩專班) === 98 === Search engine has become an essential tool in searching web page for internet users. However, the webpage that appeared is not always what the users desired. But the search engine list these pages on top of the search result after the search process, this made internet users click and browse the website that does not suit their needs, hence valuable time were wasted and the search efficiency of search engine is also lowered.
In this thesis, we analyzed the Cloaking Spam and Redirection Spam and identify their rules through experiment. Furthermore, two different types of experiments were designed which is used to detect Cloaking Spam and Redirection Spam. The result and features of Cloaking Spam and Redirection Spam were recorded. Based on these features, generalized rules were created to automatically detect Cloaking Spam and Redirection Spam.
Technology of Web Spam will continue to evolve, the Web Spam detection research will have to follow its pace. The main purpose of Web Spam is to improve website ranking on search engine. Therefore, in the future, if all the pages can be researched and analyzed with all the Spam rule identified. By placing them directly on the search engine’s crawler, this will allow search engines to filter web spam when ranking web pages, hence will reduce the probability of web spam appears in the search engine.
|
|---|
