A recommendation model based on site semantics and usage mining

The explosive growth of online data and the diversity of goals that may be pursued over the web have significantly increased the monetary value of the web traffic. To tap into this accelerating market, web site operators try to increase their traffic by customizing their sites to the needs of specific users. Web site customization Involves three great challenges: (I) the accurate identification of the user Interests in the sites' content (II) the detection of the user goals in their site visits and (III) the encapsulation of the user interests and goals into the sites' presentation and content. In this paper, we study how we can effectively identify the user interests and goals in their site visits and we evaluate their correlation as this is exemplified in the users' navigational patterns and the site's semantic content and structure. Based on our findings we propose a novel recommendation mechanism that employs web mining techniques for suggesting customized site views that satisfy both the user preferences and goals. Our experimental evaluation shows that the user site interests and interaction goals can be accurately detected from the users' navigational behavior and that our recommendation model, which uses the identified user preferences and goals yields significant improvements in the sites' usability.