Abstract
Recommender system users who rate items across disjoint domains face a privacy risk analogous to the one that occurs with statistical database queries. It combines one user's ratings of products or services with ratings of products or services with ratings from other users to answer queries with predictions and suggestions. Hence, a graph-theoretic model is used to study the benefit from and risk to straddlers.
Original language | English (US) |
---|---|
Pages (from-to) | 54-62 |
Number of pages | 9 |
Journal | IEEE Internet Computing |
Volume | 5 |
Issue number | 6 |
DOIs | |
State | Published - Nov 2001 |