Authors : Hayder M. Naji and Ghaidaa A. Al-Sultany
Abstract: Collaborative filtering recommendation system shares the user’s interests and recommends items to a user based on the interests of the other users whom are similar to his/her owntendencies. Basically, the Personalized Page Rank Algorithm (PPR) suggests items with respect to the target user by personalizing him/her only. In this study, Iteratively with each target user, the remaining users are personalized according to their rating patterns by supporting them withnew Personalized Parameters (PP). The personalized parameters have a role of personalized measure from which each user’s rank will affect and be affected on the other user’s ranks depending on the PP values. The achievement of more accurate recommender system needsmore personalization to satisfy user’s tendencies so we Present a Personalized Recommendation system using PPR algorithm with more personalization method. Finally, classification accuracy measures have been used to evaluate the outcome top-N recommendation list on a MovieLens dataset in comparison with the outcome of traditional PPR.
Hayder M. Naji and Ghaidaa A. Al-Sultany, 2017. Collaborative Filtering Recommendation using Personalized Page Rank Algorithm with New Personalized Parameters. Journal of Engineering and Applied Sciences, 12: 4108-4112.