通过挖掘Web日志改进站点结构

Improve the Organization of the Web-site by Mining Web-log

在一些商业站点中Web页面的结构有时与用户的浏览习惯不相一致,即用户在某个位置去寻找某个特定的页面,而这个页面却实际在另一个位置。该文提出一种算法找出站点中那些实际位置与用户期望位置不相一致的页面。算法的主要思想是如果访问者没有在特定的位置找到所需的页面就会回退,把这个产生回退的位置作为访问者希望相应的页面内容出现的可能的候选期望位置。然后站点管理者可以改进站点的结构,在用户的期望位置增加相应的页面的连接,这样可以使用户能够较为方便地找到所期望的页面。

Sometimes the organization of the website does not accord with the users' navigating habits——visitors try to find certain page in certain location, but that is not the pages' actual location. This article proposes an algorithm to find pages whose locations are different from where visitors expect to find them. The key insight is that the visitors will drawback if they do not find the page where they expect it. The location where the visitors drawback is just the possible expected location for the page. The administrator of the website can improve the organization , add corresponding links in the locations that visitors expect, then the visitors can navigate their expected pages more efficiently.