Building recommendation systems using peer-to-peer shared content

Peer-to-Peer (p2p) networks are used for sharing content by millions of users. Often, meta-data used for searching is missing or wrong, making it difficult for users to find content. Moreover, this abundance makes searching for new content almost impossible. Recommender systems are not unable to handle p2p data due to inherent difficulties, such as implicit ranking, noise and the extreme dimensions and sparseness of the network. This paper introduces methods for using p2p data in recommender systems. We present a method for creating contentsimilarity graph while overcoming inherent noise. Using this graph, a clustering method is presented for detecting proximity between files using the “wisdom-of-the-crowds”. Eval

• Type: Journal
• Year: 2010
• Where: CIKM
• Authors: Yuval Shavitt, Ela Weinsberg, Udi Weinsberg
• Keywords: CIKM 2010, Information Technology, Inherent Difficulties, P2p Data, Recommender Systems