Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Skip to main content
  • Dr. Ossama Embarak works as a university professor with PhD in computing[AI, ML, and data mining] from Heriot-Watt Un... moreedit
ABSTRACT Web recommendation systems aim to find the most interesting and valuable information for web users based on their collected preferences. Although, the collaborative filtering approach is the widely used, but it suffers from... more
ABSTRACT Web recommendation systems aim to find the most interesting and valuable information for web users based on their collected preferences. Although, the collaborative filtering approach is the widely used, but it suffers from several problems, one of these problems is known as the cold start problem (for example, if a new user visit Amazon web site for first time, then the Amazon system becomes unable to generate recommendations). We suggested the active node technique as a method of solution to the cold start problem, and we integrate collected users' preferences within a semantic structure, and we compare between non-semantic and semantic structure of the active node method based on three criteria novelty, coverage, and precision of generated recommendations. We found that the semantic structure achieve higher performance than non- semantic.
ABSTRACT Recommendation systems become essential in web applications that provide mass services, and aim to suggest automatic items (services) of interest to users. The most popular used technique in such systems is the collaborative... more
ABSTRACT Recommendation systems become essential in web applications that provide mass services, and aim to suggest automatic items (services) of interest to users. The most popular used technique in such systems is the collaborative filtering (CF) technique, which suffer from some problems such as the cold-start problem, the privacy problem, the user identification problem, the scalability problem, etc. In this paper, we address the cold-start problem by giving recommendations to any new users who have no stored preferences, or recommending items that no user of the community has seen yet. While there have been lots of studies to solve the cold start problem, but it solved only item-cold start, or user-cold start, also provided solutions still suffer from the privacy problem. Therefore, we developed a privacy protected model to solve the cold start problem (in both cases user and item cold start). We suggested two types of recommendation (node recommendation and batch recommendation), and we compared the suggested method with three other alternative methods (Triadic Aspect Method, Naïve Filterbots Method, and MediaScout Stereotype Method), and we used dataset collected from online web news to generate recommendations based on our method and based on the other alternative three methods. We calculated level of novelty, coverage, and precision. We found that our method achieved higher level of novelty in the batch recommendation whilst it achieved higher levels of coverage and precision in the node recommendations technique comparing to these three methods.
Recommendation systems become essential in web applications that provide mass services, and aim to suggest automatic items (services) of interest to users. The most popular used technique in such systems is the collaborative filtering... more
Recommendation systems become essential in web applications that provide mass services, and aim to suggest automatic items (services) of interest to users. The most popular used technique in such systems is the collaborative filtering (CF) technique, which suffer from some problems such as the cold-start problem, the privacy problem, the user identification problem, the scalability problem, etc. In this paper, we address the cold-start problem by giving recommendations to any new users who have no stored preferences, or recommending items that no user of the community has seen yet. While there have been lots of studies to solve the cold start problem, but it solved only item-cold start, or user-cold start, also provided solutions still suffer from the privacy problem. Therefore, we developed a privacy protected model to solve the cold start problem (in both cases user and item cold start). We suggested two types of recommendation (node recommendation and batch recommendation), and w...
Research Interests:
ABSTRACT e-commerce systems provide tremendous products to thousands of visitor 24/7. These systems still suffers from many problems such as the cold start problem, over personalization problem, privacy problem, etc. In this paper we... more
ABSTRACT e-commerce systems provide tremendous products to thousands of visitor 24/7. These systems still suffers from many problems such as the cold start problem, over personalization problem, privacy problem, etc. In this paper we provided a semantic structure in order to provide semantic based recommendations, which depend not only on items semantic structure but also on users' preferences which encapsulated within the items semantic structure. We evaluated novelty, precision, and coverage of the generated semantic recommendations and we found that semantic recommendations achieved higher performance.
ABSTRACT Web recommendation systems are affected by privacy concerns and legislations. In this paper, we suggested integration between abstract users' preferences and the website semantic structure, which enable us to identify... more
ABSTRACT Web recommendation systems are affected by privacy concerns and legislations. In this paper, we suggested integration between abstract users' preferences and the website semantic structure, which enable us to identify users' power of thinking on specific items. Web personalization systems aim to provide users with what they are looking for on a specific web site. Therefore we collected abstract users' preferences, which are used to create users' integrated routes. These integrated routes were injected into the websites semantics. Users' browsing targets are used to identify them, and also they are used to generate personal recommendations. Our experimental results showed that users are highly satisfied with the use of their power of thinking to provide recommendations, instead of using their demographic information.