A Survey on Web Pattern Mining Authors
Neha Mishra · 2013
Web mining can be described as the process of discovering and analyzing useful information from the World Wide Web. Web mining can be classified into three categories: web structure mining, web usage mining and web content mining. Web usage mining is basically used to find the navigational behavior of the user on the World Wide Web which can be used to personalize web pages. The web usage mining process includes pre- processing of web log data. After that frequent item discovery, frequent sequence discovery and frequent sub tree discovery steps are being carried out. Patterns are extracted by pattern analysis tools from the web log data. Various pattern discovery techniques are applied on the web log data. Various algorithms have been discovered for web usage mining. Page rank algorithm can be used to provide ranking to a web page. The ranking of a page depends upon the number of back links pointing to a particular page. Another algorithm which is most commonly used is HITS algorithm which calculates the hub pages as well as the authoritative pages. FP tree algorithm is used to generate a candidate generate and test tree which provides the sequence of the web pages in which they are accessed. Another approach is to calculate the significant interval and confidence which can be used to discover frequent patterns in web log data.