تحسين نظام مقترحات هجين باستخدام خورازمية الترتيب PageRank == Hybrid Recommender System Enhancement Using Personalized PageRank Algorithm
Author name:
حیدر مجید ناجي
Supervisor name:
غیداء عبد الحسین بلال
General topic:
Computer Science
Specific topic:
Information Technology
Degree:
Master
University:
University of Babylon - Information Technology Collage - Department Of Software
Language:
English
University location:
Babylon
First pages:
28T779 - p.pdf
Abstract:
Recommendation system is an information filtering system. PageRank Algorithm is useful method for the recommendation task. PageRank algorithm is used to improve the representation of movies and users in the graph network in addition to ranking movies for a target user in the recommendation activity. User preferences has been calculated based on movies genres as a part of building the user profile from his past history of rating (content analysis), and for each user, this preference was used to produce a personalized initial pagerank value for each movie instead of the traditional static equal initial pagerank value which is the first stage of iterative personalize pagerank algorithmIn addition to personalize the target user, new way has been presented to personalize each user with different weight according to them rating on movies, by supporting the proposed recommender system with a new personalize parameters for each user, which is the manner of the collaborative filter approach.To evaluate the performance of the proposed recommender system and measure the accuracy of recommendations, precision, recall and F - Measure metrics has been used. MovieLens2K dataset used to evaluate the recommendation system, it has 10,197 movies and 2,113 users, in average of 85 movie rating per user.The experimental results showing that, there is a significant improvement for the recommendations process, which is mean hybrid recommender system using personalized pagerank (HRS - PPR) is better than the traditional recommender system using personalized pagerank.
