Research on personalized web page recommendation algorithm based on user context and collaborative filtering

Nowadays web portals contain large amount of information that is meant for various visitors or groups of visitors [4]. To effectively navigate within the content the website needs to “know” its users in order to provide personalized content to them. We proposed a personalized web page recommendation model based on user context and collaborative filtering, aimed at predicting the next request of pages that web users are potentially interested in when surfing the web. We proposed an improved Collaborative Filtering (CF) algorithm to discover the similar users´ interested web page sets of the target user, based on which, a target user´s Collaborative Filtering web Page Set (CFPS) is filtered. To recommend user current interested pages, we introduced context factor to match web pages in the website. And a Merge Sort Algorithm (MSA) is proposed to merge two candidate web page recommendation sets. A thorough experimental evaluation conducted on a large real dataset demonstrates the precision and the accuracy of recommendation results.