An-Najah Staff

In this paper, we propose P2Prec, a recommendation service for P2P content sharing systems  that  exploits  users’  social  data.  The  key  idea  is  to  recommend  to  a  user  high  quality documents in a specific topic using ratings of friends (or friends of friends) who are expert in that topic. To manage users’ social data, we rely on Friend - Of- A- Friend (FOAF) descriptions. P2Prec has a hybrid P2P architecture to work on top of any P2P content sharing system. It combines efficient DHT indexing to manage the users’ FOAF files with gossip robustness to disseminate the topics of expertise between friends. In our experimental evaluation, using the CiteSeer dataset, we show that P2Prec has the ability to get the maximum recall with very good performance . Furthermore, it increases recall and precision by a factor of 2 compared with centralized solutions.