Web Pattern Extraction and Storage

Web data provides information and knowledge to improve the web site content and structure. Indeed, it eventually contains knowledge which suggests changes that makes a web site more efficient and effective to attract and retain visitors. Making use of a Data Webhouse or a web analytics solution, it is possible to store statistical information concerning the behaviour of users in a website. Likewise, through applying web mining algorithms, interesting patterns can be discovered, interpreted and transformed into useful knowledge. On the other hand, web data include quantities of irrelevant but complex data preprocessing that must be applied in order to model and understand visitor browsing behaviour. Nevertheless, there are many ways to pre-process web data and model the browsing behaviour, hence different patterns can be obtained depending on which model is used. In this sense, a knowledge representation is necessary to store and manipulate web patterns. Generally, different patterns are discovered by using distinct web mining techniques on web data with dissimilar treatments. Consequently, patterns meta-data are relevant to manipulate the discovered knowledge. In this chapter, topics like feature selection, web mining techniques, models characterisation and pattern management will be covered in order to build a repository that stores patterns’ meta-data. Specifically, a Pattern Webhouse that facilitates knowledge management in the web environment.