No abstract

No abstract

As the size of web increases along with number of users, it is very much essential for the website owners to better understand their customers so that they can provide better service, and also enhance the quality of the website. To achieve this they depend on the web access log files. The web access log files can be mined to extract interesting pattern so that the user behaviour can be understood. This paper presents an overview of web usage mining and also provides a survey of the pattern extraction algorithms used for web usage mining.

No abstract

Web page recommendation systems are used to recommend the future web page views to World Wide Web (WWW) users. Existing personalized web page recommendation systems are still limited to several problems such as, cold start, sparse data structures (Sparsity), and no diversity in the set of recommended items (Content Overspecialization). In order to overcome these difficulties, we proposed a new personalized web recommendation system by considering the different contributions of the training samples (MSNBC dataset, and castings technology international dataset). At first, the web pages are converted into number of sequences. An effective clustering algorithm called as Possibilistic Fuzzy C-Means (PFCM) is employed to identify the neighbourhood of each user profile. Then the association rule mining technique, Rapid Frequent Pattern Growth (RFPG) algorithm is used for mining the frequent web pages. Finally, the experimental outcome shows that the proposed approach delivers the high priority of web pages and also recommends the related web pages. Finally, the experimental outcome shows that the proposed approach improved accuracy in web page recommendation up to 50-60% compared to the existing methods.